Music Information Research Lab
We work on the following research topics: music information retrieval, singing voice synthesis, audio source separation, music and audio processing.
Our current challenges are:
- Exploit the multimodal character of music to enhance its automatic processing.
- Reduce the semantic gap between automatic features and user descriptors through user-centered paradigms.
- Connect music description and music creation.
- Incorporate advanced learning techniques for music processing (source separation).
- Apply our current know-how on singing voice modelling to statistical-based modelling of animal vocalizations.