English
Français The AAO (Audio, Acoustical and Waves) research group gathers digital signal processing activities for audio, biomedical and heterogeneous multimodal signals.
It aims, In particular, at developing digital audio signal processing methods in order to propose innovative solutions to the main problems linked to audio (speech, music,…) in multimedia applications. Our interests encompass the complete processing chain from sound capture and transmission to sound restitution.
Work is conducted on both a methodological level to develop new sound representations and models especially for musical signals on their application to practical problems. In particular, the group is interested in Adaptive methods for high resolution sinusoidal components tracking, sparse representations, Non-Negative Matrix factorization or hierarchical models and on their application to practical problems such as automatic indexing, compression or EEG signal processing. Source separation also appears to be at the heart of this research group with contributions at the methodological level and with applications in nearly all the individual research themes.
Audio and multimedia scenes analysis and indexing currently is the central research theme of the group and includes topics such as broadcast streams segmentation into broad classes of audio events (speech/music/silence/singing,…), musical signals automatic analysis, decomposition and understanding (polyphonic audio source separation, rhythm extraction, multiple fundamental frequencies estimation, main melody extraction,…).
A new transverse orientation has also gained more interest on the specific theme of statistical methods for signal processing with specific applications to audio and biomedical signals.
For more informations, please check
We also propose a set of tools, software and databases for audio signal processing. If interested, please check the following link:
