How can a machine make musically intelligent decisions? Signal-adaptive algorithms with customized automatic default settings are the future of producing, mixing, and processing audio for consumption. Data-driven approaches to musical creativity for music processing and generation may shape the next generation of tools for composition, production, and live music making.

Publications

• Chen, Zhiqian; Wu, Chih-Wei; Lu, Yen-Cheng; Lerch, Alexander; Lu, Chang-Tien, Learning to Fuse Music Genres with Generative Adversarial Dual Learning, Proceedings of the International Conference on Data Mining (ICDM), Institute of Electrical and Electronics Engineers (IEEE), New Orleans, 2017.
• Wu, C.-W., Vinton, M., Blind Bandwidth Extension using K-Means and Support Vector Regression, Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, New Orleans, 2017
• Laguna, C.; Lerch, A., "An Efficient Algorithm for Clipping Detection and Declipping Audio," Proceedings of the 141st AES Convention, Los Angeles, 2016