Audio Data Analysis and Signal Processing

The ADASP team (Audio Data Analysis and Signal Processing, formerly known as the AAO group) develops data analysis methods primarily targeting audio data. These developments rely on signal processing and machine learning techniques, focusing on:

  •  data decomposition and representation learning methods, especially sparse representation learning,
  • as well as parametric modelling methods.

Such methods are used essentially to address two types of tasks:

  • source separation,
  • human activity-related scene and content analysis, notably using classification methods,

with applications in:

  • machine listening,
  • music information retrieval,
  • heterogeneous, multiview or multimodal data analysis, especially multimedia content analysis,
  • physiological signal analysis, especially M/EEG data,
  • audio signal transformation (denoising, enhancement, dereverberation, spatialisation),
  • musical acoustics.

The group maintains tight links with a number of academic partners  (New York University, Technical University of Berlin, Queen Mary University of London, Dublin City University, ESPCI, IRCAM, INRIA-IRISA, INRIA-LORIA, INRIA-LORIA, CEA (Neurospin), INRIA-Parietal) and industrial partners (Technicolor, INA, Orange, RTL, Audionamix, Arkamys, Parrot,. . .). These collaborations are often developed within national and international collaborative projects 

For more information, please check

We also propose a set of tools, software and datasets for data analysis, especially audio signal processing. Check the following link: