Music Informatics Projects

Music Information Retrieval

Music Information Retrieval

How to teach a computer to listen to music? How can it understand the musical and emotional content of music and what do we learn from this? These are the questions answered by ongoing research with individual topics ranging from drum transcription and playing technique detection to automatic chord recognition.

Publications

Intelligent Music Processing

Intelligent Music Processing

Signal-adaptive algorithms with customized automatic default settings are the future of producing, mixing, and processing audio for consumption. We look into how we can make audio processing more intelligent.

Publications

Interactive Real-Time Assessment for Music Ensembles

Interactive Real-Time Assessment for Music Performance

With the prevalence of mobile technology and the wired classrooms, we use mobile technology and the application of advanced audio analysis techniques to create a software platform in which students in a vocal ensemble receive a real-time assessment of the accuracy of their singing. Through this, teachers have real-time results from individual members in their choir, allowing more efficient and more targeted teaching techniques. Ultimately, the students receive individualized feedback and instruction they would likely not receive in a large ensemble and the teacher will have a clearer understanding of the needs of the ensemble.

Contributors

  • Tim Hsu, Ashis Pati, Jonny Wang, Somesh Ganesh

Student Music Performance Assessment

Student Music Performance Assessment

The qualitative assessment of music performances is a task that is influenced by technical correctness, deviations from established performance standards, and aesthetic judgment. Despite its inherently subjective nature, a quantitative overall assessment is often desired, as exemplified by U.S. all-state auditions or other competitions. A model that automatically generates assessments from the audio data allows for objective assessments and enables musically intelligent computer-assisted practice sessions for students learning an instrument.

This research aims to characterize the performance with well-established and custom-designed audio features, model expert assessments of student performances, and predict the assessment of unknown audio recordings. Results could lead to more general software music tutoring systems that do not require score information for the assessment of student music performances.

Publications

  • Wu, C.-W.; Gururani, S.; Laguna, C.; Pati, A.; Vidwans, A.; Lerch, A., Towards the Objective Assessment of Music Performances, Proceedings of the International Conference on Music Perception and Cognition (ICMPC), San Francisco, 2016