As discussed at the last steering committee meeting, we invite our LISTEN partners to an ADASP meeting which will be held in two parts:

  • Presentation of the work of six PhD students
  • Summary of papers presented at the 2022 edition of INTERSPEECH (conference on speech processing topics) by Salah Zaiem, PhD student at ADASP

Programme of PhD presentations:

Florian Angulo (BruitParif), “Multiview learning of distributed deep embeddings for urban sound event recognition, separation and tracking”





David Perera, “Semi-supervised sound event detection and classification”





Félix Mathieu, “Audio projection in neural networks: case of source separation”





Achille Aknin, “Stochastic reverberation models for audio dereverberation”





Salah Zaiem, “Automatic data augmentation and self-supervised learning”





Morgan Buisson, “Learning audio representations for music structure analysis with low supervision”






Alain Riou (Sony CSL), “Self-supervised learning of musical representations for controllable music generation”