Titre: Deep learning for music audio signal processing
As in many fields, deep neural networks have allowed important advances in the processing of musical audio signals. We first present the specificities of these signals and some elements of audio signal processing (as used in the traditional machine-learning approach. We then show how deep neural networks (in particular convolutional neural networks) can be used to perform feature learning. We first recall the fundamental differences between 2D images and time/frequency representations. We then discuss the choice of input (spectrogram, CQT, or raw-waveform), the choice of convolutional filter shape, autoregressive neural models, and the different ways of injecting a priori knowledge (harmonicity, source/filter) into these networks.
Finally, we illustrate the different learning paradigms used in the music audio domain: classification, encoder-decoder (source separation, constraints on latent space), metric learning (triplet loss), and semi-supervised learning.
A propos de Geoffroy Peeters
Geoffroy Peeters est Professeur à TelecomParis et a été directeur de recherche durant plusieurs année à l’IRCAM (UMR STMS). Il intervient ponctuellement au Collège de France dans la chaire science des données de Stephane Mallat.
- Date: 01/12/2021
- Lieu: IBISC, site IBGBI, grand amphithéâtre et à distance via Collaborate
- Invitants et organisateurs: Blaise HANCZAR (PR Univ. Évry, IBISC équipe AROB@S et Dominique FOURER (MCF Univ. Évry, IBISC équipe SIAM)
- Présentation du séminaire et de Geoffroy Peeters (au format PDF)
