Past Seminars
Fall 2023
August 21 - Alexandria Smith
August 28 - Henrik Van Cole (virtual)
September 4 - Labor Day
September 11- Jeff Albert
September 18 - Philippe Pasquier (virtual)
September Blair Kaneshiro (virtual)
October 2 - Laura Emmery
October 9 - Fall Break
October 16 - Jeff Snyder
October 23 - Brittney Allen, Nicolette Cash, Yiwei Din
October 30 - Xuedan Gao, Shimiao Liu, Yifeng Yu
November 6 - Jingyan Xu, Danielle Leinwander, Pavan Seshadri
November 13 - Yilong Tang (BSMS), Ripken Walker (BSMS), Joseph Steele
November 20 - Shan Jiang, Nikhil Krishnan, Dhruv Pargai
November 27 - Jiarui Xu, Jiaying Li
Fall 2022
August 29 - Diyi Yang - Building Positive and Responsible Language Technologies
Abstract: Recent advances in natural language processing especially around big models have enabled extensive successful applications. However, there are a growing amount of evidences and concerns towards the negative aspects of NLP systems such as biases and the lack of input from users. How can we build NLP systems that are more aware of human factors and more trustworthy? Our recent work takes a closer look at the social aspect of language via two studies towards building more positive and responsible language technologies. The first one utilizes participatory design to construct a corpus for African American Vernacular English to study dialect disparity, and the second one examines positive reframing by neutralizing a negative point of view and generating a more positive perspective without contradicting the original meaning.
Bio: Diyi Yang is an assistant professor in the School of Interactive Computing at Georgia Tech. She received her PhD from Language Technologies Institute at Carnegie Mellon University in 2019. Her research interests are computational social science and natural language processing. Her research goal is to understand the social aspects of language and to build socially aware NLP systems to better support human-human and human-computer interaction. Her work has received multiple best paper nominations or awards at ACL, ICWSM, EMNLP, SIGCHI, and CSCW. She is a recipient of Forbes 30 under 30 in Science (2020), IEEE “AI 10 to Watch” (2020), the Intel Rising Star Faculty Award (2021), Microsoft Research Faculty Fellowship (2021), and NSF CAREER Award (2022).
September 5 - Labor Day
September 12 - Kahyun Choi
Abstract:Recently, music complexity has drawn attention from researchers in the field of Music Digital Libraries. In particular, computational methods to measure music complexity have been studied to provide better music services in large-scale music digital libraries. However, the majority of music complexity research has focused on audio-related facets of music, while song lyrics have been rarely considered. Based on the observation that most popular songs contain lyrics, whose different levels of complexity contribute to the overall music complexity, this talk will discuss how to define song lyric complexity and how to measure it computationally. In particular, this talk will focus on the concreteness and the semantic coherence of song lyrics. Finally, the answers to the following questions will be presented: 1) is there an inverted-U relationship between preference and lyric complexity? 2) what is a general trend of lyric complexity? and 3) what is the relationship between lyrics complexity and genres?
Bio: Kahyun Choi is an assistant professor and 2022 Luddy Fellow in the Department of Information and Library Science and Data Science Program at Indiana University Bloomington. She earned her Ph.D. in the School of Information Sciences at the University of Illinois at Urbana-Champaign. Before her Ph.D., she also worked as a software engineer in Naver, a search engine company in Korea. Her research interests include ethical AI workflow for Libraries, Archives, and Museums (LAMs), music information retrieval, public library-based AI education program, computational lyrics analysis, and computational poetry analysis. Her research applies computational methods and machine learning algorithms to audio and text data. She has received awards and fellowships, including the 2021 Institute of Museum and Library Services (IMLS) National Leadership Grant, 2021 Luddy Faculty Fellowship, and 2022 IMLS Early Career Research Development Project Grant.
September 19 - Allie Bashuk
Fall 2022 Seminars
August 22 - Peter Knees - Music Information Retrieval and Recommendation: Recent and Future Development
Abstract: Music information retrieval allows to build new tools for music creation and appreciation based on information in music and how people perceive and interact with it. In this talk, I will present recent research directions in music information retrieval and recommendation at my lab, touching upon various topics such as semantic control of music generation systems, deep learning architectures for music tagging, and reproducibility of user studies in MIR. I will also highlight upcoming projects, such as transformer-based drum pattern generation, sequential music recommendation, and chill factor detection in music to identify common research interests with the faculty at the School of Music.
Bio:
Peter Knees is an Associate Professor of the Faculty of Informatics, TU Wien, Austria and a Visiting Assistant Professor at Georgia Institute of Technology – School of Music for the fall term 2022. He holds a Master's degree in Computer Science from TU Wien and a PhD in the same field from Johannes Kepler University Linz, Austria. For almost two decades, he has been an active member of the Music Information Retrieval research community, reaching out to the related fields of multimedia and text information retrieval, recommender systems, and the digital arts. His research activities center on music search engines and interfaces as well as music recommender systems, and more recently, on smart(er) tools for music creation. He is one of the proponents of the Digital Humanism initiative of the Faculty of Informatics at TU Wien.
Further information: https://www.ifs.tuwien.ac.at/~knees/
August 29 - Diyi Yang - Building Positive and Responsible Language Technologies
Abstract: Recent advances in natural language processing especially around big models have enabled extensive successful applications. However, there are a growing amount of evidences and concerns towards the negative aspects of NLP systems such as biases and the lack of input from users. How can we build NLP systems that are more aware of human factors and more trustworthy? Our recent work takes a closer look at the social aspect of language via two studies towards building more positive and responsible language technologies. The first one utilizes participatory design to construct a corpus for African American Vernacular English to study dialect disparity, and the second one examines positive reframing by neutralizing a negative point of view and generating a more positive perspective without contradicting the original meaning.
Bio: Diyi Yang is an assistant professor in the School of Interactive Computing at Georgia Tech. She received her PhD from Language Technologies Institute at Carnegie Mellon University in 2019. Her research interests are computational social science and natural language processing. Her research goal is to understand the social aspects of language and to build socially aware NLP systems to better support human-human and human-computer interaction. Her work has received multiple best paper nominations or awards at ACL, ICWSM, EMNLP, SIGCHI, and CSCW. She is a recipient of Forbes 30 under 30 in Science (2020), IEEE “AI 10 to Watch” (2020), the Intel Rising Star Faculty Award (2021), Microsoft Research Faculty Fellowship (2021), and NSF CAREER Award (2022).
September 5 - Labor Day
September 12 - Kahyun Choi
Abstract:Recently, music complexity has drawn attention from researchers in the field of Music Digital Libraries. In particular, computational methods to measure music complexity have been studied to provide better music services in large-scale music digital libraries. However, the majority of music complexity research has focused on audio-related facets of music, while song lyrics have been rarely considered. Based on the observation that most popular songs contain lyrics, whose different levels of complexity contribute to the overall music complexity, this talk will discuss how to define song lyric complexity and how to measure it computationally. In particular, this talk will focus on the concreteness and the semantic coherence of song lyrics. Finally, the answers to the following questions will be presented: 1) is there an inverted-U relationship between preference and lyric complexity? 2) what is a general trend of lyric complexity? and 3) what is the relationship between lyrics complexity and genres?
Bio: Kahyun Choi is an assistant professor and 2022 Luddy Fellow in the Department of Information and Library Science and Data Science Program at Indiana University Bloomington. She earned her Ph.D. in the School of Information Sciences at the University of Illinois at Urbana-Champaign. Before her Ph.D., she also worked as a software engineer in Naver, a search engine company in Korea. Her research interests include ethical AI workflow for Libraries, Archives, and Museums (LAMs), music information retrieval, public library-based AI education program, computational lyrics analysis, and computational poetry analysis. Her research applies computational methods and machine learning algorithms to audio and text data. She has received awards and fellowships, including the 2021 Institute of Museum and Library Services (IMLS) National Leadership Grant, 2021 Luddy Faculty Fellowship, and 2022 IMLS Early Career Research Development Project Grant.
September 19 - Allie Bashuk
September 26 - Nashlie Sephus
Abstract:
October 3 | Saksham, Shawn, Bowen |
October 10 | Vedant, Shan |
October 17 | Fall Break |
October 24 | Neha, Xinyu, Ethan |
October 31 | Sile, Michael, Nikhil |
November 7 | Sean, Tilman, Lnhao |
November 14 | Rose, Jocelyn, Virgil |
November 21 | Noel, Joann, Qinyng |
November 28 | Bryce, Jaui Xu, Kelian, Rosa |
December 5 | Hsing Huang, Nitin, Rhythm, Matthew |
Spring 2022 Seminars
January 10 - Mark Riedl - Entertainment Intelligence Lab, Georgia Tech
Abstract: Computational creativity is the art, science, philosophy and engineering of computational systems which, by taking on particular responsibilities, exhibit behaviors that unbiased observers would deem to be creative. In this talk, we look at some of the particular properties that AI systems might need to be considered creative. I illustrate these properties through the lens of current research in automated story generation. I conclude the talk by discussing a method for gauging progress in building computational creativity systems
Bio: Dr. Mark Riedl is a Professor in the Georgia Tech School of Interactive Computing and Associate Director of the Georgia Tech Machine Learning Center. Dr. Riedl’s research focuses on human-centered artificial intelligence—the development of artificial intelligence and machine learning technologies that understand and interact with human users in more natural ways. Dr. Riedl’s recent work has focused on story understanding and generation, computational creativity, explainable AI, and teaching virtual agents to behave safely.
January 24 - Joycelyn Willson - Hip Hop Studies, Georgia Tech (Virtual)
Title: Understanding Hip Hop at 50 and Why it Matters
Abstract: Hip hop is trending, and it has been since at least the early 1990s. To get really nit picky about it, rap music has had a grip on popular culture since 1982 when “The Message” dropped as the first hip hop song with political commentary. Then, it peaked at number 62 on Billboard’s Hot 100 and stayed there for 7 weeks, as “Planet Rock” peaked on Billboard's Hot 100 two months later at number 48 and spent 11 weeks on the chart. Forty years later, Cardi B’s “Up” sat at #2 for weeks on Billboard’s Hot 100, and hip hop/r&B is responsible for 25% of the music consumption as rock steadies at 23%. Trap music - as a benchmark for representing the cultural lifestyle and political proclivities of a generation - has remained one of Atlanta’s most significant contributions to global hip hop. It’s safe to say the grip Hip Hop has on music and culture is now more like a stronghold - a stronghold that is amplified across industries outside of music including education, technology, politics, design thinking, and architecture. How was an artform/lifestyle/way of looking at the world/generation/culture gotten so big that, as a music genre, has surpassed rock n roll? What is it about its adaptive qualities that map so perfectly to areas like advertising and marketing such that Flo-rida’s “Low” is remixed as a Kroger greatest hit? What is hip hop, proper, and how does it work?
Bio: Joycelyn Wilson is an integrative curriculum designer, essayist, music journalist, and assistant professor of hip hop studies and digital media in the School of Literature, Media, and Communication at Georgia Tech. She is an expert in African-American music and performance, Black maker culture, as well as African-American education and schooling in the American South. She also focuses on the culture, race, and technology of her home city Atlanta. Her scholarship has implications across STEAM, methodologies of humanistic inquiry, archival preservation, and curriculum design; areas that been published across academic and popular platforms including Teachers College Press, UGA Press, International Journal of Africana Studies, and Routledge. Her essays on culture, arts, and technology have been published by Billboard, The Root, InStyle, and Google Arts & Culture. Dr. Wilson is a co-producer of the Emmy-nominated docufilm “Walking With Guns, produced in collaboration with UN Ambassador and former Atlanta mayor Andrew Young. Her current research leverages the connections between hip hop's techno-pedagogical affordances and relationships to design thinking in computational and creative media-making. She has contributed commentary to MSBNC, Netflix's Hip Hop Evolution, VH1's ATL Rise, and TV-One's UnSung. Beyond pop culture, Atlanta hip-hop and hip-hop’s intersection with politics and culture, Dr. Wilson examines the cultural histories of civil rights and social justice in the South, Black maker culture/design thinking, media, and technology. She is the founder of the Four Four Beat Labs and HipHop2020 Innovation Archive, and available to broadly discuss topics related to digital archiving and preservation.
January 31 - Rick Beato - Music YouTuber
Abstract: This talk will center around a conversation on the impact of technology in recorded music and the relative impact of those changes on music’s ability to communicate. Quantized and auto-tuned current music is often referred to as having been made “more perfect” but as it communicates less I’d argue that it is in fact less perfect. It will close with a discussion, leading into questions from the audience, about the idea of a Turing test for music.
Bio: Rick Beato is an American YouTube personality, music professional, and educator. Since the early 1980s, he has worked variously as a musician, songwriter, audio engineer and record producer. Beato lives in Georgia, United States. He has written songs with, and produced music for, a variety of musical artists, including Needtobreathe, Parmalee, and Shinedown.
Beato was born into a large family from Rochester, New York. He studied at Ithaca College, obtaining a bachelor of arts degree in music. He earned a master's degree in jazz studies from the New England Conservatory of Music in 1987.
Beato began his YouTube career in 2015 after posting a video of his eldest child, Dylan, who is able to identify individual notes within complex chords after just one hearing.This video of his son's display of perfect pitch received 21 million views, causing Beato to decide to parlay his social media fame into a full-fledged YouTube channel. He posted his first YouTube video on June 8, 2016. On August 27, 2019, Beato received the Golden Play Button from YouTube when he achieved 1 million subscribers. As of August 2021, the YouTube channel has 2.5 million subscribers.
Beato's channel is under his own name, although he introduces every video with the title "Everything Music". One series in the channel is called What Makes This Song Great?, in which Beato deconstructs and discusses the elements of popular songs. The videos in the series regularly get over one million views.
In one video, Beato enlists the help of Bon Jovi guitarist Phil X and virtuoso guitarist Eric Johnson to re-interpret the guitar solo on Led Zeppelin's iconic "Stairway to Heaven". Beato and Phil X play the guitar solo in the styles of Peter Frampton and Eddie Van Halen, respectively, while Johnson plays it in his own style.
Beato has been vocal about what he believes are problems with the enforcement of copyright law, and its application on the YouTube platform. Several of his videos, including those about Radiohead and Fleetwood Mac, were issued take-down notices because of copyright claims.
In July 2020, Beato testified about his experiences on YouTube before a United States Senate Committee on the Judiciary reviewing the Digital Millennium Copyright Act considering limitations and exceptions like fair use.
February 7 - Mike Winters - Microsoft Research, Alum (Virtual)
Abstract:
How can we design musical instruments that help us solve the most pressing issues facing humanity? I think music’s capacity to elicit empathy may help. In this talk, I will present my work over several years expressing social, affective and neurophysiological signals through sound. I will introduce this topic through a "Sonification of Emotion," which uses musical cues to convey continuous arousal and valence measures. I will then generalize the approach and show how sound can be used to display emotional information in a range of complex systems and processes, from activations in Convolutional Neural Networks to the realtime neural synchrony. I will also present the results of a study on auditory heartbeats, which demonstrates the ability for even simple musical cues like tempo to elicit empathic responses. When applied as an empathic technology, music may help connect us to the affective information in processes and systems we can't normally hear.Bio:
R. Michael Winters is a Post Doctoral Researcher at Microsoft Research, part of the Audio & Acoustics and Brain-Computer Interface Groups. Before joining Microsoft, Mike was a research affiliate at the Socioneural Physiology Lab, part of the Kinsey Institute at Indiana University. In 2020, he graduated with a PhD from the Georgia Institute of Technology, where he was part of the Brain Music Lab, Sonification Lab and Robotic Musicianship Group. Prior to that he received an MA from McGill University where he worked at the Center for Interdisciplinary Research in Music Media and Technology (CIRMMT) in the Input Devices and Music Interaction Lab (IDMIL). Over the years he has consulted at interned with a variety of industrial research partners including Sennheiser, Microsoft Research, Georgia Tech Research Institute, Hop Labs and the PhET Project. He has developed numerous instruments that support learning, performance and social connection through novel auditory experiences with information. His research spans behavioral psychology and neurophysiology at the frontiers of audio interaction design (AUX) for mobile brain/body interfaces (MoBI), artificial intelligence (AI) and augmented/virtual reality (AR/VR).
Portfolio: mikewinters.io
February 14 - Eran Egozy - MIT, Harmonix Co-founder (Virtual)
Bio: E RAN EGOZY , Professor of the Practice in Music Technology, is an entrepreneur, musician, and technologist. He is the co - founder and chief scientist of Harmonix Music Systems, the music - based video game company that created the revolutionary titles Guitar Hero , Rock Band , and Dance Central with sales in excess of one billion dollars. Eran and his business partner Alex Rigopulos were named in Time Magazine's Time 100 and Fortune Magazine's Top 40 Under 40. Eran is also an accomplished clarinetist, performing regularly with Radi us Ensemble, Emmanuel Music, and freelancing in the Boston area. Prior to starting Harmonix, Eran earned degrees in Electrical Engineering and Music from MIT, where he conducted research on combining music and technology at the MIT Media Lab. Now back at M IT, his research and teaching interests include interactive music systems, music information retrieval, and multimodal musical expression and engagement. His current research project, ConcertCue, is a program - note streaming mobile app for live classical mu sic concerts that has been featured with the Boston Symphony Orchestra and New World Symphony.
February 21 - Walker Davis, Alex Mitchel - Co-founders Boomy (Virtual)
Title: Powering the Next 100 Billion Songs with Music Automation
Abstract: Boomy is a music creation and distribution platform that enables users of any experience level to produce and publish original music. Founder and CEO Alex Mitchell will discuss Boomy’s business model and strategy. Director of Music Automation Walker Davis will present algorithmic approaches to composition and mixing/production.
Alex Jae Mitchell is the founder and CEO of Boomy Corporation (boomy.com), a company developing music automation technologies using artificial intelligence. Mitchell is a serial music entrepreneur who previously founded Audiokite Research, the leading market research platform for independent music. Mitchell has worked with a number of music and media brands in consulting and advisory capacities, including Artiphon, Shady Records / Goliath Artists, DotBC/Verifi Media, Reflex Group, Krantz Media Group, Infinite Album, Riff, and others.
Boomy Director of Music Automation, Walker Davis, is a multi-instrumentalist, hip hop/electronic music producer, algorithmic composer, and visual artist. He received his Bachelor’s of Music from UC Irvine in Jazz Saxophone Performance, and his Master’s of Arts in Music, Science, Technology from CCRMA, Stanford. Walker’s work at Boomy includes low-level audio software development, algorithmic composition and mixing design/implementation, and content creation of all things music-related.
February 28 - Jeannette Yen - Biologically Inspired Design Lab, Georgia Tech
March 7 - Hsing Hung, Nitin, Bryce
March 14 - Jiarui Xu, Rhythm, Matthew
March 21 - Spring Break
March 28 - Kelian, Rosa, Qinying
March 4 - Virgil, Jason Smith
April 11 - John, Amber
April 18 - Amit, Tim
April 25 - Alison, Mason
Fall 2021 Seminars
August 23 - Jane Foley
Abstract: For this talk, Jane will focus on the conceptual underpinnings of finding and making sounds by deep-diving into a few of her projects to show how a project begins as a question and becomes a reality. Foley's work is very process-oriented and always comes back around to the 'whys' and the 'whats' of sound, as well as the craft of 'how' to find a sound. She is interested in the condition of an artist as a curious explorer, and fascinated by sound as a spacious medium that can hold many questions.
Bio: Jane Foley (b. 1985, New Orleans, they/she) is a sculpture, sound, and new media artist living in Atlanta, Georgia (US). Jane has created sound sculptures for the Architecture Triennale in Lisbon, Portugal and La Friche Belle de Mai in Marseille, France with Zurich-based Sound Development City, as well as produced a sound composition that played in taxicabs throughout the 5th Marrakech Biennale. In Atlanta, they have created public works for the High Museum, Dashboard Co-op, The Atlanta Contemporary, and the Hartsfield-Jackson Atlanta Airport, among others. Foley currently teaches graphic design at Emory University after having recently completed an MFA program, studying interdisciplinary sculpture and sound, at the School of the Art Institute of Chicago. Foley’s sound works explore isolation versus connectivity in public spaces, beginning with deep listening through field recordings and spontaneous collaborations. They often travel to approach underdog histories of places through the lens of recorded sound, which has taken them to many distant areas including remote Iceland, Lisbon, Marseille, rural Georgia, and Linz, Austria. They then interpret these sonic artifacts into sound sculptures and video installations– physical spaces made to suit each sound. Drawing on their experience as a former college synchronized swimmer, Foley has recently been exploring swimming pools as sonic sites, using sensitive underwater microphones and video to capture the swimmer as an acoustic instrument.
August 30 - Jason Borenstein
Abstract: In the session, the speaker will discuss ethical issues related to conducting research. A brief overview of topics in the realm of Responsible Conduct of Research (RCR) will be provided with the main focus being on the ethics of human subjects research and research misconduct.
Bio: Jason Borenstein, Ph.D., is the Director of Graduate Research Ethics Programs at the Georgia Institute of Technology. His appointment is divided between the School of Public Policy and the Office of Graduate Studies. He has directed the Institute's Responsible Conduct of Research (RCR) Program since 2006 and is part of the leadership team for the Ethics, Technology, and Human Interaction Center (ETHICx). Dr. Borenstein is a member of Association for Practical and Professional Ethics (APPE) Board of Directors, Chair of the APPE Research Integrity Scholars and Educators (RISE) Consortium, and a member of the IEEE SSIT Technical Committee on Ethics/Human Values. His teaching and research interests include robot & artificial intelligence ethics, engineering ethics, research ethics/RCR, and bioethics.
September 13 - Alex Westner (video)
Abstract: This seminar will take you on a whirlwind journey through my career that began in music technology, expanded into audio technology, took a hard right into FinTech, and is now focused on augmented reality for hearing loss. In rapid fire, we'll cover microphone arrays—for good and for evil; getting strangers to sing, teaching technology to understand music; academia vs. industry; product management; product positioning; guitar distortion in Forza; the T-Pain Effect; user-driven design; business modeling; running lean; people vs. passion; AR for hearing loss; and full circle back to microphone arrays.
Bio: Alex Westner is an audio technologist, entrepreneur, and an expert in product strategy. He recently founded Xander, a startup with a mission to create a new bionic superpower to help people listen and understand. Throughout his 20-year career, Alex has shipped dozens of products that analyze and enhance speech and music—including iZotope RX, known in the industry as the Photoshop for sound, so integral for production it earned an Engineering Emmy award. Prior to that, he earned an MS degree from the MIT Media Lab studying the “cocktail party effect”—the human brain's ability to focus on one sound while filtering out other competing noises.
September 20 - Kris Bowers (video)
Bio: Kris Bowers is an award-winning film score composer and pianist known for his thought-provoking playing style, creating genre-defying film compositions that pay homage to his classical and jazz roots. Bowers has composed music for film, television, documentary, and video games collaborating with musicians and artists across genres, including Jay Z, Kanye West, Kobe Bryant, Mahershala Ali, Justin Simien, and Ava DuVernay. His works include The Snowy Day (for which he won the Daytime Emmy Award for Outstanding Music Direction and Composition in 2017), Dear White People, Green Book, When They See Us, Black Monday, Madden NFL 20, Mrs. America, Bridgerton, Bad Hair , The United States vs. Billie Holiday, Space Jam: A New Legacy, Respect, and King Richard. In 2020, Bowers codirected the documentary short film, A Concerto is A Conversation, with documentary filmmaker Ben Proudfoot. The film, a New York Times Op-Doc – executive produced by Ava DuVernay, premiered at the 2021 Sundance Film Festival and was an Academy Award nominee for Best Documentary (Short Subject) at the 93rd Academy Awards.
September 27 - Joycelyn Wilson
Bio: Joycelyn Wilson is an integrative curriculum designer, essayist, music journalist, and assistant professor of hip hop studies and digital media in the School of Literature, Media, and Communication at Georgia Tech. She is an expert in African-American music and performance, Black maker culture, as well as African-American education and schooling in the American South. She also focuses on the culture, race, and technology of her home city Atlanta. Her scholarship has implications across STEAM, methodologies of humanistic inquiry, archival preservation, and curriculum design; areas that been published across academic and popular platforms including Teachers College Press, UGA Press, International Journal of Africana Studies, and Routledge. Her essays on culture, arts, and technology have been published by Billboard, The Root, InStyle, and Google Arts & Culture. Dr. Wilson is a co-producer of the Emmy-nominated docufilm “Walking With Guns, produced in collaboration with UN Ambassador and former Atlanta mayor Andrew Young. Her current research leverages the connections between hip hop's techno-pedagogical affordances and relationships to design thinking in computational and creative media-making. She has contributed commentary to MSBNC, Netflix's Hip Hop Evolution, VH1's ATL Rise, and TV-One's UnSung. Beyond pop culture, Atlanta hip-hop and hip-hop’s intersection with politics and culture, Dr. Wilson examines the cultural histories of civil rights and social justice in the South, Black maker culture/design thinking, media, and technology. She is the founder of the Four Four Beat Labs and HipHop2020 Innovation Archive, and available to broadly discuss topics related to digital archiving and preservation.
Title: Understanding Hip Hop at 50 and Why it Matters
Abstract: Hip hop is trending, and it has been since at least the early 1990s. To get really nit picky about it, rap music has had a grip on popular culture since 1982 when “The Message” dropped as the first hip hop song with political commentary. Then, it peaked at number 62 on Billboard’s Hot 100 and stayed there for 7 weeks, as “Planet Rock” peaked on Billboard's Hot 100 two months later at number 48 and spent 11 weeks on the chart. Forty years later, Cardi B’s “Up” sat at #2 for weeks on Billboard’s Hot 100, and hip hop/r&B is responsible for 25% of the music consumption as rock steadies at 23%. Trap music - as a benchmark for representing the cultural lifestyle and political proclivities of a generation - has remained one of Atlanta’s most significant contributions to global hip hop. It’s safe to say the grip Hip Hop has on music and culture is now more like a stronghold - a stronghold that is amplified across industries outside of music including education, technology, politics, design thinking, and architecture. How was an artform/lifestyle/way of looking at the world/generation/culture gotten so big that, as a music genre, has surpassed rock n roll? What is it about its adaptive qualities that map so perfectly to areas like advertising and marketing such that Flo-rida’s “Low” is remixed as a Kroger greatest hit? What is hip hop, proper, and how does it work?October 4 - Ian, BeachOctober 11 - Fall Break
October 18 - Gary Kamikawa
Bio: Gary Kamikawa has served as the cross-channel marketing tech leader for Amazon Music since December 2018. Gary leads a tech team focused on the vision of delivering personalized experiences that create genuine value for our customers (incl. potential ones) and turns listeners into engaged fans. To accomplish this, his team invests in automation and personalization of the major touchpoints Music has with a customer including email, mobile push, in-app messaging, Music’s web properties, and personalization across Amazon.com. Prior to Amazon, Gary has led marketing automation and demand gen, at other companies including 9 years at Microsoft delivering marketing tech capabilities starting with Office 365, and extended across Windows and Xbox. Gary has held a variety of marketing and engineering leadership roles across the full spectrum of startup, mid-size and enterprise companies. In Gary’s spare time, when he’s not occupied with the many aquatic adventures he has with his family, you might find him playing some tunes on his tuba from his days as a music performance major at University of Washington, or listening to Alt & Classic rock while he tries to avoid hitting another slice on the golf course.
October 25 - Ash, Lauren
November 1 - ISMIR talks
November 8 - Alison, Mason, Amit
November 15 - Tim, John, Amber
November 12 - Amy, Virgil
November 29 - Sophia, Mohammad
December 6 - Contingency
Spring 2021 Seminars
Jan 25 - Teresa Marrin Nakra
Title: Transcending the Past & Passing it Forward: creative applications of technology in music
Abstract: One of the most important concepts with which to engage in music technology is when to borrow from the past and when to transcend it. Prior models do still have a lot to teach us, even as we proceed to invent the future. The trick is to carefully select which bits to emulate and which bits to leave behind. This talk will describe my experimental approach to integrating classical music and technology, including my quantitative studies of orchestral conducting and application of gesture models to interactive music systems. I will describe the “Conductor’s Jacket” sensor interface that measured the gestures and signals of conductors, and other interactive systems for the gestural creation of music. I will also describe how I pass these ideas forward through my work with college students, and how I am taking next steps toward a more inclusive and creative approach to music-making with technology.
Bio: Teresa Marrin Nakra is the Coordinator of Music Technology and Associate Professor of Music & Interactive Multimedia at The College of New Jersey. Her courses and projects focus on creative applications of technology to music performance, composition, education, and human-centered design. Her students have gone on to advanced study in music tech grad programs, as well as careers in audio & media production, acoustics, and composition for films and video games. Teresa studied Music at Harvard, where she founded a conductor training orchestra, conducted three opera productions, and received a Michael Rockefeller Memorial Fellowship. After college, she earned M.S. and Ph.D. degrees at the MIT Media Lab with fellowships from IBM, Motorola, and Interval Research. During those years, she appeared in 160 performances of Tod Machover’s Brain Opera and served as a musical coach for Penn & Teller. Teresa has made important research contributions in the study of musical expression and gesture. She is best known for her quantitative analyses of orchestral conducting and their application to interactive music systems. Her invention, the “Conductor’s Jacket,” was featured in the MIT150 Exhibition celebrating MIT's founding, and is now held in the permanent collection of the MIT Museum. Her patent on the Digital Baton was cited as prior art for the Nintendo Wii-mote and used to defend Nintendo patents in cases heard by the International Trade Commission. Teresa has presented her work in concert with the Boston Pops and Boston Symphony Orchestras, and has built interactive conducting systems for the public to experience in museums and concert halls.
Feb 1 - Mary Farbood
Title: Timbre and Musical Tension
Abstract: This talk discusses a series of studies that explores how timbre contributes to the perception of musical tension. Tension is an aggregate of a wide range of musical and auditory features and is a fundamental aspect of how listeners interpret and enjoy music. Timbre as a contributor to musical tension has received relatively little attention from an empirical perspective compared to other musical features such as melodic contour and harmony. The studies described here explore how common timbre descriptors contribute to tension perception. Multiple features including spectral centroid, inharmonicity, and roughness were examined through listener evaluations of tension in both artificially generated stimuli and electroacoustic works by well-known composers such as Stockhausen and Nono. Timbral tension was further examined in an audiovisual context by pairing electroacoustic compositions with abstract animations.
Bio:Morwaread Farbood is Associate Professor and Associate Director of the Music Technology program at New York University, where she is affiliated with the NYU Music and Audio Research Laboratory (MARL) and the Max Planck/NYU Center for Language, Music, and Emotion (CLaME). Her research focuses primarily on understanding the real-time aspects of music listening, in particular how emergent phenomena such as tonality and musical tension are perceived, in addition to developing computer applications for facilitating musical creativity based on cognitive models. Her publications have appeared in a variety of journals including Music Perception, Journal of the Acoustical Society of America, Journal of Experimental Psychology: Human Perception and Performance, Frontiers in Psychology, Frontiers in Neuroscience, Attention, Perception, & Psychophysics, Personal and Ubiquitous Computing, and IEEE Computer Graphics and Applications. As a harpsichordist, Farbood won First Prize in the 2005 Prague Spring International Harpsichord Competition and is the recipient of the Pro Musicis International Award.
Feb 8 - Asante Bradford
Bio: Asante Bradford is Project Manager for Digital Entertainment and Emerging Media for the Georgia Department of Economic Development, the sales and marketing arm for the State of Georgia. The Global Commerce Division conducts extensive business development, sales, marketing and promotional activities in order to attract entertainment projects and businesses to the state. The division’s team also assists the local, national and international entertainment industries with information, expertise and resources. Asante helps promote the growth of the digital media industry as well as identify initiatives that will help grow businesses for the state of Georgia in interactive entertainment and eSports. He also helps educate potential prospects and provide clients with information about the Georgia Entertainment Industry Incentives Act. His area of concentration with the Global Commerce office is to increase the impact of interactive entertainment for the State of Georgia as well as being a dedicated liaison to assist with promotions, logistics and business development for attracting digital media companies outside the state to relocate in Georgia.
Feb 15 - Akito Van Toyer (Alum)
Title: Music, Wonder, and Machines
Abstract: This talk describes my journey in exploring experimental interactive music systems that enable Musical Wonderers (i.e., anyone interested in music, regardless of their skill levels) to learn how to play intuitively and encourages them to develop advanced skills and sound production techniques through unguided practice. I will cover several instances of those interactive music systems such as a mixed reality environment that offers unique and rich immersive experiences, a massive musical collaboration platform that encourages players to listen to their cities and create music with environmental sounds, and an electromechanical musical instrument that transforms found objects into musical materials. This presentation will also highlight theories, methodologies, and potential applications of interactive music systems that stimulate open creativity and provide meaningful directions that guide users to learn underlying principles about music and sound manipulation.
Bio: Akito van Troyer is an Assistant Professor of Electronic Production and Design at Berklee College of Music. His interdisciplinary research focuses on the exploration and development of new musical experiences that enrich people's lives and impact the future of human expression. Akito conducts and accomplishes his research through innovations in the fields of musical instrument design, music production, performance, and audience participation. He obtained his Ph.D. degree from the MIT Media Lab in 2018, designing and building innovative interactive music systems that inspire and guide people in discovering their own musical language. Akito previously completed his Masters through the MIT Media Lab in 2012, designing new performance systems that encourage audience participation and augment the experience of audience members through interconnected networks. He also earned a Masters degree in 2010 from the Georgia Tech Center for Music Technology, building computer- and text-based live performance platforms for laptop orchestra.
Feb 22 - Xavier Serra
Title: Research on sound and music understanding at the MTG
Abstract: In this talk I will give an overview of the research being done at the Music Technology Group of the Pompeu Fabra University in Barcelona related to the analysis and description of sound and music signals, combining signal processing and machine learning methods. We work both on data-driven methodologies, in which the development and use of large data collections is a fundamental aspect, and on knowledge-driven approaches, in which domain knowledge of the problem to be addressed is needed. Combining these research approaches, we are able to tackle practical problems related to automatic sound and music description, music exploration and recommendation, and tools for supporting music education.
Bio: Xavier Serra is a Professor of the Department of Information and Communication Technologies and Director of the Music Technology Group at the Universitat Pompeu Fabra in Barcelona. After a multidisciplinary academic education, he obtained a PhD in Computer Music from Stanford University in 1989 with a dissertation on the spectral processing of musical sounds that is considered a key reference in the field. His research interests cover the computational analysis, description, and synthesis of sound and music signals, with a balance between basic and applied research and approaches from both scientific/technological and humanistic/artistic disciplines. Dr. Serra is very active in the fields of Audio Signal Processing, Sound and Music Computing, Music Information Retrieval and Computational Musicology at the local and international levels, being involved in the editorial board of a number of journals and conferences and giving lectures on current and future challenges of these fields. He was awarded an Advanced Grant from the European Research Council to carry out the project CompMusic aimed at promoting multicultural approaches in music information research. More info: https://www.upf.edu/web/xavier-serra
Mar 1 - Tyler White, Ryan Rose, Scot Driscoll (Alumni)
Bio: Tyler White
As a music enthusiast and analytical thinker, Tyler sought a career merging the two. He graduated with an EE degree from Southern Polytechnic State University while working as the sole solid-state amplifier repair technician for Orange Amplifiers. He attended the GTCMT graduate program, where he was a member of the Robotic Musicianship group and held a GRA position. Here, he was a part of the Robotic Third Arm Drummer research team and responsible for the electronic, firmware, and control system design, as well as creating the interactive composition and performing with the arm. Shortly after graduation, Tyler went to work for Bose's Automotive Division as an Applied Research and Concept Development DSP Engineer. He is a part of the Active Sound Management group, which designs cancellation systems to reduce in-cabin vehicle noise, systems to enhance vehicle sounds and auditory feedback cues, demonstrates in-vehicle prototypes to OEM customers, and assists in the product development cycle. In his spare time, he likes to spend time with his wife, travel, play music, snowboard, and golf.
Bio: Ryan Rose
Ryan Rose is a musician, technologist, and tinkerer living in Cambridge, MA. By day he is a cloud software engineer at Bose, and by night he explores musical expression through connected web experiences, physical installations, robots, and more.
Bio: Scott Driscoll
Scott Driscoll, a founder and development manager at Foundry 45, has been passionate about technology and teaching his whole career. After graduating with master of science degrees in mechanical engineering and music technology from Georgia Tech, he founded a DIY electronics company with a mission to enable anyone to make electronics, creating how-to videos now seen more than 16 million times. He developed a deep interest in augmented reality and virtual reality (VR) and has spent more than eight years coding and leading teams to create immersive training experiences. That includes Foundry 45, which develops enterprise-level VR training experiences for Fortune 500 companies. He has organized and run several meetups in Atlanta, including the XR Atlanta and Atlanta Bitcoin groups.
Mar 8 - Lisa Margulis
Title: Hearing Music NarrativelyBio: Elizabeth Hellmuth Margulis is a Professor at Princeton University, where she directs the Music Cognition Lab. Her research approaches music from the combined perspectives of music theory/musicology and cognitive science. Her book On Repeat: How Music Plays the Mind (Oxford University Press) received the 2014 Wallace Berry Award from the Society for Music Theory, and the 2015 ASCAP Deems Taylor/Virgil Thomson Award. Her latest book The Psychology of Music: A Very Short Introduction (Oxford University Press) was published in 2018 and has been translated into Spanish, Hungarian, Japanese, and, soon, Chinese. Her cross-cultural research on narrative perceptions of music is supported by a grant from the National Science Foundation. She has been a Kavli Fellow of the National Academy of Sciences as well as a National Endowment for the Humanities Summer Scholar.
Mar 15 - Youngmoo Kim
Title: Broadening the Impact of Music Technology
Abstract: Technology is now inseparable from media and entertainment, with entire industries emerging to provide on-demand content as well as recommendations using the content and machine learning / AI. But moving beyond streaming, novel interaction technologies and robotic systems are enabling new types of live and hybrid digital-physical artistic performances. All of these applications require not just technical knowledge, but also domain-specific expertise in music, performance, live theater, etc. At the Expressive & Creative Interaction Technologies (ExCITe) Center at Drexel University, we pursue transdisciplinary arts–technology collaborations, particularly with such external partners as the Philadelphia Orchestra, Opera Philadelphia, and Parsons Dance. In this talk, I will highlight a range of projects resulting from these collaborations, from PhD research with professional artists to fully inclusive STEAM (STEM+Arts) education programs for K-12 students, as well as new forms of creative media that have emerged from the social distancing constraints of the COVID-19 pandemic.
Bio: Youngmoo Kim is Director of the ExCITe Center at Drexel University, an institute at for transdisciplinary collaboration, and Professor of Electrical & Computer Engineering. His research group, the Music & Entertainment Technology Laboratory (MET-lab), pursues AI for music, human-machine interfaces and robotics for expressive interaction, and STEAM education. He has also served as Resident Technologist for Opera Philadelphia and is an advisor for the Philadelphia Museum of Art. He was a member of the National Academies committee for “Branches from the Same Tree”, a 2018 report on the integration of the Humanities & Arts with Sciences, Engineering, and Medicine in Higher Education. Youngmoo also has extensive experience in vocal music performance, including performances with the Tanglewood Festival Chorus and SpeakEasy Stage Company (Boston) and currently sings with The Tonics, an a cappella ensemble in Philadelphia. In response to the coronavirus pandemic, he developed Virtual Chorister, a smartphone app for remote music collaboration, and launched “Creating at a Distance”, a biweekly newsletter highlighting creative & collaborative work in the era of social distancing.
Mar 22 - Yiting, Tess
Mar 29 - Yihao, Sandeep
April 5 - Yilin, Lauren
April 12 - Amy, Daniel
April 19 - Sophia, Mohammad
April 26 - Laney, Rishi
Fall 2020 Seminars
17-Aug: Alumni presentation - Chris Howe, Annie Zhang
24-Aug: Alumni presentations - Hanoi Hantrakul Chih-Wei Wu
31-Aug: Peter Knees
Details
Title: Neutrality and Fairness in Music Recommendation: A Matter of Digital HumanismAbstract: Music recommenders have become a commodity for music listeners. In practice, the task of music recommendation is a multi-faceted task, serving multiple stakeholders. Besides the music listener and the publishers of the music, the service itself as well as other branches of the music industry are affected. In this talk, I will discuss the multiple aspects and stakeholders present in the process of music recommendation. I will further discuss possible impacts on academic research in this area, foremost regarding the questions of fairness, neutrality, and potential biases in datasets and illustrate aspects that should be taken into consideration when developing music recommender systems. Finally, I will link these discussions to the ongoing initiative of digital humanism that deals with the complex relationship between humans and machines.
Bio: Peter Knees is an Assistant Professor of the Faculty of Informatics, TU Wien, Austria. He holds a Master degree in Computer Science from TU Wien and a PhD in the same field from Johannes Kepler University Linz, Austria. For over 15 years, he has been an active member of the Music Information Retrieval research community, reaching out to the related fields of multimedia and text information retrieval, recommender systems, and the digital arts. His research activities center on music search engines and interfaces as well as music recommender systems, and more recently, on smart(er) tools for music creation. He is one of the proponents of the Digital Humanism initiative of the Faculty of Informatics at TU Wien.
07-Sep: Holiday
14-Sep: Psyche Loui
Details
Title: Music as a Window into Emotion and CreativityAbstract: I will describe recent efforts in my lab in which we identify the brain networks that enable strong emotional responses to music, and observe the effects of training in musical improvisation on brain and cognitive structure and function.
Bio: The neuroscience of music cognition, musical perception, pitch problems, singing, tone-deafness, music disorders and emotional impact of music and the voice, comprise much of Psyche Loui’s research and work. What happens in the brain when we create music? What gives some people a chill when they are moved by music? Can music be used to help with psychiatric and neurological disorders? These are questions that Loui tackles in the lab. Director of the MIND Lab (Music, Imaging and Neural Dynamics) at Northeastern University, Loui has published in the journals Current Biology, Journal of Neuroscience, Journal of Cognitive Neuroscience, NeuroImage, Frontiers in Psychology, Current Neurology and Neuroscience Reports, Music Perception, Annuals of the New York Academy of Sciences, and others. For her research on music and the brain, Loui has been interviewed by the Associated Press, CNN, WNYC, the Boston Globe, BBC Radio 4, NBC news and CBS radio, and the Scientist magazine. Loui graduated the University of California, Berkeley with her PhD in Psychology (Specialization: Cognition, Brain and Behavior) and attended Duke University as an undergraduate graduating with degrees in Psychology and Music and a certificate in Neuroscience. She has since held faculty positions in Psychology, Neuroscience, and Integrative Sciences at Wesleyan University, and in Neurology at the Beth Israel Deaconess Medical Center and Harvard Medical School.
21-Sep: Amy Belfi
Details
Title: Investigating the timecourse of aesthetic judgments of musicAbstract: When listening to a piece of music, we typically make an aesthetic judgment of it – for example, within a few seconds of hearing a new piece, you may determine whether you like or dislike it. In the present talk, I will discuss several lines of work focusing on when and how listeners make aesthetic judgments of music, and which musical and contextual factors contribute to these judgments. First, I will discuss work indicating that listeners can make accurate and stable aesthetic judgments in as little as several hundred milliseconds. Next, I will discuss work suggesting that the emotional valence of a piece of music contributes strongly to its aesthetic appeal. Finally, I will focus on ongoing work investigating differences in listener judgments of live versus recorded music.
Bio: Amy Belfi is an Assistant Professor in the Department of Psychological Science at Missouri S&T. She received her B.A. in Psychology from St. Olaf College, her Ph.D. in Neuroscience from the University of Iowa, and completed postdoctoral training at New York University. Her work covers a broad range of topics relating to music perception and cognition, including music and autobiographical memory, aesthetic judgments of music, and musical anhedonia.
28-Sep: David Sears
Details
Title: Expectations for tonal harmony: Does order matter? Mingling corpus methods with behavioral experimentsAbstract: An extensive body of research has repeatedly demonstrated that a tonal context (e.g., I-IV-V in C major) primes listeners to expect a tonally related target chord (I in C major). Tillmann and Bigand (2001) have shown, however, that scrambling the order of chords in the context fails to slow the speed and accuracy of processing. Given recent claims emerging out of corpus studies of tonal harmony that temporal order is a fundamental organizing principle in many musical styles, this talk will address whether listeners exploit this principle to generate predictions about what might happen next. To that end, I will present the results of behavioral studies that replicate Tillmann and Bigand’s experimental design, but train a probabilistic model on a large corpus of chord annotations to select the scrambled conditions. Our findings contradict those from Tillmann and Bigand’s study, suggesting listeners may internalize the temporal dependencies between chords in the tonal system.
Bio: David Sears is Assistant Professor in Interdisciplinary Arts at Texas Tech University. He directs the Performing Arts Research Lab (PeARL) with Dr. Peter Martens. His research interests include music perception and cognition, computational approaches to music theory and analysis, emotion and psychophysiology, and sensorimotor synchronization.
05-Oct: ISMIR papers presentations
12-Oct: Chris White
Details
Abstract: Meter is a phenomenon of patterns. In general, music theorists imagine meter as arising from a series of consistently paced accents, as involving a listener who expects that pacing to continue into the future, and as grouping adjacent pulses to form a hierarchy of stronger and weaker pulses. Relying on these patterns, the computational approach of autocorrelation has been used by researchers and audio engineers to identify the meter of musical passages. This technique finds periodicities with which similar events tend to occur. For instance, the approach would consider a piece in which similar events tend to recur at the remove of the whole note, half note, and quarter note as being in 4/4 meter. My talk will outline how to implement this computational task on symbolic musical data, and then discuss certain parameters that can be adjusted depending on the engineering goals (e.g., tracking patterns of loudness verses patterns of harmonic change). I end by noting that this approach also requires an a priori definition of “accent” in order to discern relatively strong pulses from relatively weak ones, something that has provocative connections to how musical learners understand and internalize musical meter.
Bio: Chris White is Assistant Professor of Music Theory at the University of Massachusetts Amherst, having received degrees from Yale, Queens College–CUNY, and Oberlin College Conservatory of Music. His articles have appeared in many venues including Music Perception, Music Theory Online, and Music Theory Spectrum. His research investigates algorithmic and linguistic theories of music by presenting computational models of musical style, function, meter, and communication. Chris' work has also focused on geometrically modeling early 20th-century musics, especially the music of Alexander Scriabin. Additionally, Chris is an avid organist, having studied with Haskell Thompson and James David Christie. As a member of the Three Penny Chorus and Orchestra, he has appeared on NBC's Today Show and as a quarterfinalist on America's Got Talent.
19-Oct: Student presentations - Pranav, Lisa
26-Oct: Student presentation - Virgil, Tejas
02-Nov: Student presentation - Tianxue, Yiting
09-Nov: Student presentation - Sandeep, Lauren, Yihao
16-Nov: Student presentation - Yilin, Daniel, Rishi
23-Nov: Student presentation - Sophia, Laney
Fall 2019 Seminars
August 18 - Domnhail Hernon, Bell Labs
August 26 - Nat Condit-Schultz, Visiting Assistant Professor, School of Music
September 09 - Jason Freeman, Professor and Chair, School of Music
September 16 - Alexander Lerch, Associate Professor, School of Music
September 23 - Jfly (How Big is Your Dream)
September 30 - Sang Leigh
October 7 - Ning, Ash, Beach
October 21 - Shauna, Li Chia
October 28 - Diemo Schwarz (IRCAM)
November 4 - Kaushal, Tejas, Snehesh
November 11 - Antoine, Aziz, Yifei
November 18 - Pranav, Chalece, Raghav
November 25 - Jiawen, Yanchao, Jason Smith
Spring 2019 Seminars
January 7 - Gil Weinberg, Professor and Director, Center for Music Technology
January 14 - Grace Leslie, Assistant Professor, School of Music
January 28 - Joe Plazak
- Abstract: Interdisciplinary research on music encompasses a diverse array of domains and applications, both within academia and industry. Despite commonalities and many shared objectives, the questions, methods, and results of academic & industry research are often starkly different. This talk anecdotally highlights some of the quirks within these two worlds, while also posting a number of in-demand research skills for the coming future. The first half of the talk will focus on the speaker's past academic research related to affective audio communication; the second half will focus on industry research related to teaching computers how to read and write music notation.
- Bio: Joe Plazak is a Senior Software Engineer and Designer at Avid Technology, where he spends his days drinking coffee and teaching computers how to read, write and perform music via the world's leading music notation software: Sibelius. He co-designs Sibelius along with a team of world-class composers, arrangers, performers, and super-smart techies. He earned a Ph.D. in Music Perception and Cognition from the Ohio State University while researching musical affect perception and computational music analysis, and thereafter taught music theory and conducted interdisciplinary research at a small liberal arts college. After years at the front of the classroom, he returned to the back row (where he belongs) and retrained within the Gina Cody School of Engineering and Computer Science at Concordia University while researching audio-based human computer interaction and also dabbling in computational art. He is a card-carrying academia refugee, an expat, a commercial pilot and flight instructor, Superwoman's husband, and a sleep-deprived dad (which he considers to be the best job of all).
February 4 - Marybeth Gandy (Cancelled)
- Abstract: Our relationship with technology and the interfaces to them is changing dramatically as we enter an era of wearable and ubiquitous computing. In previous eras of (personal and then mobile) computing the interface designer could rely on the visual channel for conveying the majority of information, while relying on typing, pointing, and touching/swiping for input. However, as computing devices are becoming more intimately connected to our bodies and our lives, a completely new approach to user interfaces and experiences is needed. In particular, the auditory channel has been relatively unexplored as a primary modality during these previous eras, but it is important now that we learn how to best leverage additional modalities in these wearable/ubicomp systems, which must support and anticipate our needs, providing services via interfaces that do not distract us from our primary tasks. In this talk I will discuss how sophisticated auditory interfaces could be utilized in future user experiences, provide examples developed by students in the Principles of Computer Audio course, highlight the challenges inherent to audio-centric interfaces, as well as the research and development that is needed to face those challenges.
- Bio: Dr. Maribeth Gandy is the Director of the Wearable Computing Center and of the Interactive Media Technology Center within the Institute for People and Technology, and a Principal Research Scientist at Georgia Tech. She received a B.S. in Computer Engineering as well as a M.S. and Ph.D. in Computer Science from Georgia Tech. In her nineteen years as a research faculty member, her work has been focused on the intersection of technology for mobile/wearable computing, augmented reality, multi-modal human computer interaction, assistive technology, and gaming. Her interest is in achieving translational impact through her groups’ research and development via substantive collaborations with industry, helping wearable technologies to flourish outside the academic setting.
February 11 - Taka Tsuchiya
- Abstract: How can we explore and understand non-musical data with sound? Can we compose a music that tells a story about data? This study compares the methodologies for data exploration between traditional data-science approaches and the unconventional auditory approaches (i.e., sonification) with considerations such as the learnability, properties of sound, and aesthetic organization of sound for storytelling. The interactive demonstration utilizes CODAP (Common Online Data Analysis Platform), a web-based platform for data-science education and experiments, extended with the sonification plugins.
- Bio: Takahiko Tsuchiya (Taka) is a Ph.D. student working with Dr. Jason Freeman. His researches include the development of sonification frameworks and a live-coding environment. From July to December 2018, he joined the Concord Consortium, a non-profit science-education company in Emeryville, CA as part of the NSF internship program. He developed sonification plugins for their data-science platform (CODAP) while also contributing to general R&D such as the improvement of the formula engine and data visualization.
February 18 - Shachar Oren
- Abstract: Oren will share the story of Neurotic Media, the Atlanta-based music distribution company he founded over a decade ago, which has successfully navigated distribution paradigm shifts from music downloads to ringtones, lockers, and on-demand streaming. In 2018, Neurotic Media was acquired by Peloton Interactive, where the platform now serves as the ‘source of truth’ for all things music, powering a growing music-related feature-set for Peloton’s fast-growing Member community of one million worldwide. Advancements in music technology are blurring the lines between the creative process and the distribution business. While, in the past, music was packaged into physical products, boxed and sold off of shelves, music today is syndicated digitally to a growing number of smart end-points which administer data of their own. This has opened the door to a new range of creative and business possibilities. Just recently, DJ Marshmallow enjoyed over 10M live views of the concert he performed inside popular video game Fortnite, a groundbreaking event by any measure. What if tomorrow, the DJ is GA Tech’s Shimon Robot’s AI system? Endel is an example of an app that helps people focus and relax with AI-manufactured sounds, which react to data points from your phone about your environment in real time. What can your phone also add about your state of mind? Seventy percent of smart speakers in the US today feature Amazon’s Alexa, who clearly knows a lot about your personal preferences and home front in general. What new creative directions are possible when we weave AI, deep data analytics, and the human mind?
- Bio: Shachar Oren is VP of Music at Peloton, a global technology company reinventing fitness, and the CEO of its B2B music-centric subsidiary Neurotic Media. Neurotic Media successfully navigated several distribution paradigm shifts, from music downloads to ringtones, lockers, and on-demand streaming. In 2018, Neurotic Media was acquired by Peloton. Peloton instructors lead daily live streamed fitness classes with dynamic music playlists across cycling, running, bootcamp, strength, stretching, yoga and meditation – and deliver its live and on-demand programming via the company's connected fitness products, the Peloton Bike, and Peloton Tread. as well as the Peloton Digital app. The Neurotic Media Platform serves as the ‘source of truth’ for all things music within Peloton’s services. Since 2017, Shachar has served as President of Georgia Music Partners (GMP), the non-profit responsible for the Georgia music tax incentive – enabling music companies with qualified expenditures in Georgia to save 15%-30% of their cost. Shachar also serves on the Executive Advisory Board of the Georgia Tech College of Design.
February 25 - Ofir Klemperer
- Abstract: In his lecture and performance, Ofir will talk about the way our perception of music has changed with the digital age, and about the impact of computing on intuitive musical performance. Ofir then will demonstrate his way of bringing the instrumental performative practice back into electronic music, using his monophonic synthesizer, the Korg ms-20.
- Bio: Ofir Klemperer (born in Israel 1982). is a composer, improviser, singer/ song writer, and producer. He received his Bachelor and Master degrees in music composition at the Royal Conservatory of The Hague, the Netherlands. Leaning heavily on the analog synthesizer the Korg MS-20, Ofir’s music is melodic in its core, and through orchestrating classical instruments along with punk-rock and electronics, he applies to his melodies an experimental approach and Noise. Ofir’s music has been performed internationally, selected cities include: Tel Aviv, Amsterdam, Belgrade, Gent, Antwerp, Brussels, and Sao Paolo. His work has been featured at Bolzano Jazz Festival in Italy, and MATA Festival in New York City. Some of the ensembles he has written for are: Israel Contemporary Players, Civic Orchestra of Chicago, Talea Ensemble, Asko|Schoenberg Ensemble, Pow Ensemble, Rosa Ensemble, Modelo62, Ensemble Klang, and Orkest de Ereprijs. You can find Ofir’s music on ofirklemerer.bandcamp.com and ofirklemperer.wordpress.com. In 2014 Ofir moved to the United States and lived in Cincinnati, OH until 2017. He is currently located in Atlanta, Georgia.
March 4 - Colby Lieder
- Abstract: Augmenting Reality with Music and Audio Engineering -- When I was in graduate school, I always wanted to hear what guest speakers were passionate about, how they landed where they are in life, and -- if there was any resonance with these---a few tips that I could file away. So I'll follow that pattern here. :) In this talk, I'll briefly discuss my research projects in academia, recent transition to industry, and the challenges facing music and audio design in the augmented reality space.
- Bio: Composer-engineer Colby Leider works at Magic Leap, an augmented-reality startup that blends technology, physiology, and creativity to reveal worlds within our world and add magic to the everyday. He previously served as associate professor and program director of the Music Engineering Technology Program (MuE) at the University of Miami Frost School of Music for many years, where he hosted ICMA, SEAMUS, and ISMIR conferences. Colby holds degrees from Princeton (Ph.D., MFA), Dartmouth (AM), and the University of Texas (BSEE). His research interests include AR/MR/VR systems, digital audio signal processing, sound synthesis, tuning systems, and acoustic ecology, and he has received grants from the National Science Foundation, NVIDIA, the Coulter Foundation, and several corporations.
March 11 - Martin Norgaard
- Abstract: Cognitive Processes Underpinning Musical Improvisation -- Music improvisation involves the ability to adapt and integrate sounds and motor movements in real-time, concatenating previously stored motor sequences in order to flexibly produce a desired result, in this case, a particular auditory experience. The output of improvisation must then be evaluated by the musician in real time based on internal goals and the external environment, which may lead to the improviser modifying subsequent motor acts. I explore qualitative accounts of this process by expert and developing jazz musicians as well as improvisers from different cultural traditions. I then compare these descriptions with results from our related investigations using Electroencephalography and functional Magnetic Resonance Imaging. Finally, I argue that developing improvisation achievement cause positive far-transfer effects as measured by changes in executive function.
March 25 - Tejas, Avneesh
April 1 - Ryan, Yi
April 8 - Benjie, Yongliang
April 15 - Madhukesh, Jeremy
April 22- Yuqi, Keshav, Richard Yang
April 29- Jyothi
Fall 2018 Seminars
August 20 - Jason Freeman, Professor and Chair of School of Music
August 27 - Alexander Lerch, Assistant Professor, School of Music
September 10 - Gil Weinberg, Professor and Director, Center for Music Technology
- Abstract: The Robotic Musicianship Group at Georgia Tech aims to facilitate meaningful musical interactions between humans and machines, leading to novel musical experiences and outcomes. In our research, we combine computational modeling approaches for music perception, interaction, and improvisation, with novel approaches for generating acoustic responses in physical, social, and embodied manner. The motivation for this work is based on the hypothesis that real-time collaboration between human and robotic players can capitalize on the combination of their unique strengths to produce new and compelling music. Our goal is to combine human qualities such as musical expression and emotions with robotic traits such as powerful processing, mechanical virtuosity, the ability to perform sophisticated algorithmic transformations, and the capacity to utilize embodied musical cognition, where the robotic body shapes its musical cognition. The talk will feature a number of approaches we have explored for perceptual modeling, improvisation, path planning, and gestural interaction with robotic platforms such as Haile, Shimon, Shimi, Skywalker hand and the robotic drumming prosthesis.
September 17 - Grace Leslie, Assistant Professor, School of Music
- Abstract: The Georgia Tech Brain Music Lab is a community gathered around a unique facility combining EEG (brainwave data) and other physiological measurement techniques with new music technologies. Our mission is to engage in research and creative practice that brings health and well-being. This talk will present an overview of our activities at the Brain Music Lab, including sonification of physiological signals, acoustic design for health and well-being, therapeutic applications of musical stimulation, and brain-body music performance.
September 24 - Claire Arthur, Visiting Assistant Professor, School of Music
- Abstract: The computational and cognitive musicology group conducts empirical research to address questions about musical structure and/or human perception and cognition of music, with the aim of advancing our knowledge in these domains, but also in providing accessible technology and digital resources for music research, education, or creation. This talk will present an overview of the types of questions asked in the fields of computational and cognitive musicology, as well as specific examples of recent research, such as: statistical modeling of melody and harmony, voice-leading theory versus practice, measuring strong emotional responses to music, and the qualitative and quantitative differences of melodic tones in varying harmonic contexts.
October 15 - Nat Condit-Schultz, Lecturer, School of Music
October 22 - Siddharth, Ashish
October 29 - Richard, Mike
November 5 - Tejas, Benjie
November 12 - Jeremy, Yi
November 19 - Ryan, Yongliang
November 26 - Avneesh, Yuqi
December 3- Madhukesh, Keshav
Spring 2018 Seminars
January 8 - Matt Craney
- Abstract: Humanoids, Robotics, and Design for Disability -- Robotics are going through a Cambrian explosion as barriers to development are being reduced, power density and computation capacity is increasing, and controls are advancing. Applying these advancements we are simultaneously making incremental and explosive steps forward in the development of powered prostheses. This talk will give an overview of some of the work happening at the MIT Media Lab Biomechatronics group including optogenetics, new amputation paradigms, computational socket design and of course robotic legs. I will present some concepts from my core research project that I intend to apply to my collaboration with Gil Wienberg and the Robotic Musicianship program; I will talk through the development techniques I use for a multi-degree of freedom robotic prosthetic leg for above knee amputees. All of this work will be framed by some of my previous work in robotic assembly of discrete cellular lattices (digital fabrication), humanoid robotics, product design, and advanced Solidworks modeling techniques.
January 22 - Frank Hammond, Center for Robotics and Intelligent Machines, Georgia Tech
- Abstract: The field of human augmentation has become an increasingly popular research area as capabilities in human-machine interfacing and robot manufacturing evolve. Novel technologies in wearable sensors and 3D printing have enabled the development of more sophisticated augmentation devices, including teleoperated robotic surgery platforms and powered prostheses, with greater speed and economy. Despite these advances, the efficacy and adoption of human augmentation devices has been limited due to several factors including (1) lack of continuous control and dexterity in robotic end-effectors, (2) poor motion and force coordination and adaptation between robotic devices and humans, and (3) the absence of rich sensory feedback from the robotic devices to the human user. My research leverages techniques in soft machine fabrication, robotic manipulation, and mechanism design to arrive at human augmentation solutions which address these issues from a methodological perspective. This talk will highlight aspects of our design methodology including the experimental characterization of human manipulation capabilities, the design of mechanisms and devising of control strategies for improved human-robot cooperation, and new efforts to enable virtual proprioception in robotic devices – a capability which could allow humans to perceive and control robotic augmentation devices as if they were parts of their own bodies.
January 29 - Astrid Bin
- Abstract: Much has been written about digital musical instruments (DMIs) from the performer's perspective, and there has been comparatively little study on the perspective of the audience. My Ph.D. research investigated the audience experience of error in DMI performance - a playing tradition that is radically experimental and rule-breaking, leading some to suggest that errors aren't even possible. In this research I studied live audiences using a combined methodology of post-hoc data and live data, which was collected via a system I designed specifically for this purpose called Metrix. In this seminar I present this methodology, as well as some of the insights that resulted from this research on how audiences experience DMI performance, and how they perceive error in this context.
February 5 - Deantoni Parks
- Abstract: Deantoni Parks is one of the finest drummers working today, displaying a sleek intuitive balance between raw rhythmic physicality and machine-like precision. His abilities have led him to collaborations with the likes of John Cale, Sade, the Mars Volta and Flying Lotus as well as a teaching stint a the Berklee College of Music. In this workshop, Deantoni Parks will explore how musicians can augment their natural talents with technology, adopting its benefits to fuel their own vision. According to Parks, "The relationship between music and technology is always evolving, but true music cannot exist without a soul." From this philosophical starting point, Parks will engage with attendees to seek out where an equilibrium between human and machine expression lie.
February 12 - Tanner Legget (Mandala) and Daniel Kuntz (Crescendo)
February 19 - Minoru "Shino" Shinohara - Human Neuromuscular Physiology Lab, Georgia Tech
February 26 - Michael Nitsche, School of Literature, Media, and Communication, Georgia Tech
March 5 - Guthman Preparation
March 12 - Guthman Lessons Learned and Zach
March 26 - Somesh, Hanoi
April 2 - Hongzhao, Agneya
April 9 - Vinod, Takumi
April 16 - Rupak, Hanyu
April 23 - Jyoti, Henry, Joe
Fall 2017 Seminars
August 28 - Valorie Salimanpoor, Baycrest Institute
- Abstract: Music is merely a sequence of sounds, each of which contains no independent reward value, but when arranged into a sequence it is perceived as intensely pleasurable in the brain. How does a transient and fleeting sequence of sounds bring us to tears or strong physiological reactions like chills? Although music has no clear survival value, it has been a fundamental part of humanity, existing as far back as history dates (prehistoric era) and has developed spontaneously in every recorded culture. In this talk I present brain imaging research to show how sophisticated cognitive functions integrate to give rise to musical pleasure and why you cannot find two people in the world with the exact same taste in music.
September 11 - Robert Hatcher, soundcollide
- Abstract: Soundcollide’s mission is to disrupt the music creation process by breaking down barriers to collaboration, such as physical proximity. Our music technology platform will predict and enhance the performance of its users by streamlining the process of music creation and production. It accomplishes this task by increasing the amount of music that artists can create through an immersive collaborative experience where multiple users work concurrently. While the application is under load, soundcollide’s machine learning tools will analyze and compile a history of artists' procedural preferences enabling artists to discover the most compatible connections for future recording and production collaborations. Our intent is to host the largest number of concurrent users, thus increasing the accuracy and reach of our machine-learning technology.
September 18 - Clint Zeagler, Wearable Computing Center, Georgia Tech
- Abstract: Working on a wearable technology interdisciplinary project team can be challenging because of a lack of shared understanding between different fields, and a lack of ability in cross-disciplinary communication. We describe an interdisciplinary collaborative design process used for creating a wearable musical instrument with a musician. Our diverse team used drawing and example artifacts/toolkits to overcome communication and gaps in knowledge. We view this process in the frame of Susan Leigh Star’s description of a boundary object, and against a similar process used in another musical/computer science collaboration with the group Duran Duran. More information available here.
September 25 - Brian Magerko, School of Literature, Media, and Communication, Georgia Tech
- Abstract: In a future that is increasingly seeing intelligent agents involved in our education, workforce, and homes, how human productivity fits into that unfolding landscape is unclear. An ideal outcome would be one that both draws on human ingenuity, creativity, and problem solving (and definition) capabilities but also on the affordances of computational systems. This talk will explore the notion of “co-creative” relationships between humans and AI, where such a path might be found.
October 2 - Carrie Bruce, School of Interactive Computing, Georgia Tech
- Abstract: When designing for variation in human ability, accessibility is frequently the measure of success. Although accessible design can make it easier for an individual to gain access to spaces, products, and information, the emphasis is often solely on impairment and its mitigation as the basis for design. Thus, we end up with “handicapped parking”, assistive technology, and other specialized designs that can be exclusionary and do not necessarily address an individual’s participation needs – or their engagement that sustains personal identity, supports context-related motivations, and promotes inclusion. While interactive technologies have the potential to enable this type of participation, there is a lack of evidence-based design that demonstrates how this can be accomplished. My work focuses on operationalizing and designing for participation through building an evidence base and encouraging research-driven practice. I will discuss a few projects related to participation, including the Accessible Aquarium Project. I will show how we can perform user-centered, research-driven practice in designing interactive spaces, products, and information based on access and participation needs.
October 16 - Frank Hammond, Center for Robotics and Intelligent Machines, Georgia Tech
- Abstract: The field of human augmentation has become an increasingly popular research area as capabilities in human-machine interfacing and robot manufacturing evolve. Novel technologies in wearable sensing and 3D printing have enabled the development of more sophisticated augmentation devices, including teleoperated robotic surgery platforms and powered prostheses. Despite these advances, the efficacy and adoption of human augmentation devices has been limited due to several factors including (1) lack of continuous control and dexterity in robotic end-effectors, (2) poor motion and force coordination and adaptation between robotic devices and humans, and (3) the absence of rich sensory feedback from the robotic devices to the human user. My research leverages techniques in soft robot fabrication, wearable sensing systems, and non-anthropomorphic design strategies to arrive at human augmentation solutions which address the issues of device form and function from a methodological perspective. In this talk, I will highlight aspects of our powered prosthesis design methodology, including (1) the experimental characterization of human manipulation capabilities, (2) the design of mechanisms and control strategies for improved human-robot cooperation, and (3) new efforts to enable the neurointegration of robotic manipulation devices – a capability which could allow humans to perceive and control powered prostheses and extra-limb robots as if they were parts of their own bodies.
October 23 - Kinuko Masaki, SmartEar
- Abstract: With the proliferation of voice assistants (e.g. Apple's Siri, Google's Now, Amazon's Alexa, Microsoft's Cortana) and “smart” speakers (e.g. Amazon's Echo, Google's Home, Apple Homepod), people are realizing that "voice is the next frontier of computing". Voice allows for efficient and hands-free communication. However, for a voice-first device to truly replace smartphones couple of technological advancements have to be made. In particular we need to 1) be able to pick up the user’s voice commands even in loud environments and in the presence of many interfering speech, 2) understand the user’s request even when spoken in a natural conversational way, and 3) respond back to the user in a very natural and human way. This talk will articulate how advancements in artificial intelligence/deep learning, digital signal processing, and acoustics are addressing these issues and helping to make voice computing a reality.
October 30 - Hantrakul Lamtharn, Zach Kondak
November 6 - Ganesh Somesh, Hongzhao Guan, Agneya Kerure
November 13 - Masataka Goto, AIST, Japan
- Abstract: Music technologies will open the future up to new ways of enjoying music both in terms of music creation and music appreciation. In this seminar talk, I will introduce the frontiers of music technologies by showing some practical research examples, which have already been made into commercial products or made open to the public, to demonstrate how endusers can benefit from singing synthesis technologies, music understanding technologies, and music interfaces. From the viewpoint of music creation, I will demonstrate a singing synthesis system, VocaListener, and a robot singer system, VocaWatcher. I will also introduce the world's first culture in which people actively enjoy songs with synthesized singing voices as the main vocals: emerging in Japan since singing synthesis software such as Hatsune Miku based on VOCALOID has been attracting attention since 2007. Singing synthesis thus breaks down the long-cherished view that listening to a non-human singing voice is worthless. This is a feat that could not have been imagined before. In the future, other long-cherished views could also be broken down. As for music appreciation, I will demonstrate a web service for active music listening, Songle, that has analyzed more than 1,100,000 songs on music- or video-sharing services and facilitates deeper understanding of music. Songle is used to provide a web-based multimedia development framework, Songle Widget, that makes it easy to develop web-based applications with rigid music synchronization by leveraging music-understanding technologies. Songle Widget enables users to control computer-graphic animation and physical devices such as lighting devices and robot dancers in synchronization with music available on the web. I will then demonstrate a web service for large-scale music browsing, Songrium, that allows users to explore music while seeing and utilizing various relations among more than 780,000 music video clips on video-sharing services. Songrium has a three-dimensional visualization function that shows music-synchronized animation, which has already been used as a background movie in a live concert of Hatsune Miku.
November 20 - Takumi Ogatan, Vinod Subramanian, Liu Hanyu
November 27 - Rupak Vignesh, Zichen Wang, Zhao Yan
Spring 2017 Seminars
January 9: Mike Winters, Center for Music Technology Ph.D. student
- Abstract: Working with human participants is an important part of evaluating your work. However, it is not always easy to know what is ethical and not as several factors must be considered. In this talk, I will discuss ethical issues of using human participants for research from the eBelmont Report to the submitting an IRB. I will also consider the ethical issues in the projects I have worked on in the past year including a system for Image Accessibility.
January 23: Mark Riedl, Associate Professor in the School of Interactive Computing and Director of the Entertainment Intelligence Lab
- Abstract: Computational creativity is the art, science, philosophy, and engineering of computational systems that exhibit behaviors that unbiased observers would deem to be creative. We have recently seen growth in the use of machine learning to generate visual art and music. In this talk, I will overview my research on generating playable computer games. Unlike art and music, games are dynamical systems where the the user chooses how to engage with the content in a virtual world, posing new challenges and opportunities. The presentation will cover machine learning for game level generation and story generation as well as broader questions of defining creativity.
January 30: Lisa Margulis, Professor and Director of the Music Cognition Lab at the University of Arkansas
- Abstract: This talk introduces a number of behavioral methodologies for understanding the kinds of experiences people have while listening to music. It explores the ways these methodologies can illuminate experiences that are otherwise difficult to talk about. Finally, it assesses the potential and the limitations of using science to understand complex cultural phenomena.
February 6: Martin Norgaard, Assistant Professor of Music Education at Georgia State University
- Abstract: In our recent pilot study, middle school concert band students who received instruction in musical improvisation showed far-transfer enhancements in some areas of executive function related to inhibitory control and cognitive flexibility compared to other students in the same ensemble. Why does improvisation training enhance executive function over and above standard music experience? Music improvisation involves the ability to adapt and integrate sounds and motor movements in real-time, concatenating previously stored motor sequences in order to flexibly produce the desired result, in this case, a particular auditory experience. The output of improvisation must then be evaluated by the musician in real time based on internal goals and the external environment, which may lead to the improviser modifying subsequent motor acts. I explore how developing these processes could cause the observed far-transfer effects by reviewing our previous qualitative and quantitative research as well as significant theoretical frameworks related to musical improvisation.
February 13: Chris Howe, Project Engineer at Moog Music
- Abstract: Chris Howe is a project engineer at Moog Music where he helps create new musical tools to inspire creativity. He will be discussing his role as embedded systems designer on the Global Modular project, a collaboration with artist Yuri Suzuki which explores globalization through crowd-sourced sampling, convolution reverb, and spectral morphing.
February 20: Michael Casey, Professor of Music and Computer Science at Dartmouth
- Abstract: Our goal is to build brain-computer interfaces that can capture the sound in the mind's ear and render it for others to hear. While this type of mind reading sounds like science fiction, recent work by computer scientists and neuroscientists (Nishimoto et al., 2011; Haxby et al., 2014) has shown that visual features corresponding to subjects' perception of images and movies can be predicted from brain imaging data alone (fMRI). We present our research on learning stimulus encoding models of music audio from human brain imaging, for both perception and imagination of the stimuli (Casey et al., 2012; Hanke et al., 2015; Casey 2017). To encourage further development of such neural decoding methods, the code, stimuli, and high-resolution 7T fMRI data from one of our experiments have been publicly released via the OpenfMRI initiative. Prof. Casey and Neukom Fellow Dr. Gus Xia will also discuss the Neukom Institute's 2017 Turing Test in Human-Computer Music Interaction, comprising several performance tasks in instrumental music and dance. Competitors are asked to create artificial performers capable of performing “duets” with human performers, possibly in real time.
February 20: Gus Xia, Neukom Postdoc Fellow at Dartmouth
- Abstract: Expressive Human-Computer Music Interaction -- In this talk, Gus will present various of techniques to incorporate automatic accompaniment system with musical expression, including nuance timing and dynamics deviations, humanoid robotic facial and gestural expression, and basic improvisation techniques. He will also promote 2017 "Turing Test for Creative Art", which is initialized at Dartmouth college and this year contains a new track on Human-computer music performance. For more information, please visit http://bregman.dartmouth.edu/turingtests/.
February 27: Roxanne Moore, Research Engineer II at Georgia Tech
- Abstract: There are a lot of ideas out there about how to "fix" education in the United States, particularly in K-12. However, new innovations are constantly met with the age-old question: Does it work? Different stakeholders have different definitions of what it means to "work" and each of those definitions has unique measurement and assessment challenges. In this talk, we'll look at different ways of answering the "Does it work?" question in the context of different education innovations that I've personally worked on. We'll look at the innovations themselves and the research methods used to assess whether or not those innovations "work." We'll also take a complex systems view of schools, including some systems dynamics models of school settings, to better understand the challenges and opportunities in K-12 education.
March 6: Klimchak, Artist
- Abstract: Klimchak will discuss his musical compositional methods, which involve the intersection of home-built instruments, low- and high-tech sound manipulation, and live performance. He will perform 2 pieces, WaterWorks (2004) for a large bowl of amplified water, and Sticks and Tones (2016) for frame drum, melodic and laptop.
March 13 - Annie Zhan, Software Engineer at Pandora
- Abstract: Music technology has been playing a more and more important role in academic and industrial research and developments. At Pandora, we conduct lots of research around intelligent systems, machine listening, and recommendation systems. How is music information retrieval used in industrial companies? What are the key successes and challenges? This talk will cover several of my graduate research projects around MIR (music mood detection, the Shimi band), and audio fingerprinting duplicate detection system, music recommendation systems developed at Pandora.
March 27 - Avrosh Kumar, Nikhil Bhanu
- Avrosh's Abstract: The focus of this project is to develop a DAW (digital audio workstation) interface to aid audio mixing in virtual reality. The application loads an Ableton Live session and creates a representation of virtual reality, taking advantage of the depth and wider field of vision. This provides a way for audio engineers to look at the mix, visualize panning and frequency spectra from a new perspective and interact with the DAW controls using gestures.
- Nikhil's Abstract: Astral Plane is an object-based spatial audio system for live performances and improvisation. It employs Higher-Order Ambisonics and is built using Max/MSP with Ableton Live users in mind. The core idea is to create and apply metadata to sound objects (audio tracks in Live) in real-time, at signal rate. This includes object origin, position, trajectory, speed of motion, mappings etc. The novel features include interactive touch & gesture control via an iPad interface, continuous/one-shot geometric trajectories & patterns, sync with Live via Ableton Link and automatic spatialization driven by audio features extracted in real-time. The motivations are to explore the capability of stationary/moving sounds in 2D space and to assess the perceptibility of various trajectories, interaction paradigms in terms of musicality. The aim is to enable artists and DJs to engage in soundscape composition, build/release tension and storytelling. Project source and additional information is available on GitHub.
April 3 - Shi Cheng, Hua Xiao
April 10 - Milap Rane, Sirish Satyavolu
April 17 - Jonathan Wang, Shijie Wang
- Jonathan's Abstract: The focus of this project in vocal acoustics is vocal health and studying the effects of vocal disorders on the acoustic output of the human voice. For many professionals, growths on the vocal folds alter their oscillatory motion and ultimately affect the sound of their voice as well as their health. However, most people with voice disorders do not seek medical attention or treatment. My project aims to create a preliminary diagnosis tool by comparing the recording of a patient’s voice with other voice recordings.
April 24 - Brandon Westergaard, Amruta Vidwans
- Amruta’s Abstract: Dereverberation is an important pre-processing step for audio signal processing. It is critical step for speech recognition and music information retrieval (MIR) tasks. It has been a well researched topic in case of speech signals but these methods cannot be directly applied to music signals. In the previous semester evaluation of existing speech based dereverberation algorithms on music signals was carried out. In this semester the focus is towards using machine learning to perform music dereverberation. This project will be useful for MIR tasks and for audio engineers to obtain dry recordings.
May 1 - Tyler White, Lea Ikkache
- Tyler's Abstract: My project is Robotic Drumming Third Arm. The main goals and motivations are to explore how a shared control paradigm between a human drummer and wearable robotics can influence and potentially enhance a drummer’s performances and capabilities. A wearable system allows us to examine interaction beyond the visual and auditory that is explored in non-wearable robotic systems such as Shimon or systems that attach actuators directly to the drums. My contributions to this project have been a sensor fusion system, data filtering, and smoothing methods, designed and fabricated a custom PCB, created a custom firmware and hardware to communicate via from the Arduino to Max/MSP, advanced stabilization techniques for two moving bodies, and high-level musical interactivity programs for performance. Watch a short video of the project here.
- Lea's Abstract: This project revolves around a sound exhibition called Memory Palace. The application uses indoor localization systems to create a 3D sound "library" in the exhibition space. Users, with their smartphones, can, therefore, record sounds (musical or words) and place them in space. When their phone hovers around a sound someone has placed, it will play the sound. This application, based on web-audio and whose development started at IRCAM, aims to make users reflect on the subject of memory, and play with sounds and space.