ICASSP, IEEE’s International Conference on Acoustics, Speech and Signal Processing, is the world’s largest and most comprehensive technical conference focused on signal processing and its applications. Three papers will be presented this year in Brighton, with contribution of the chair’s members Slim Essid, Gaël Richard and Umut Şimşekli:

A Music Structure Informed Downbeat Tracking System Using Skip-Chain Conditional Random Fields and Deep Learning

Track: AASP: Audio and Acoustic Signal Processing
Session: Music Signal Analysis and Multimedia
Time: Wednesday, May 15, 08:30 – 10:30
Authors: Magdalena Fuentes, Brian McFee, Hélène Crayencour, Slim Essid, Juan Pablo Bello

Efficient Bayesian Model Selection in PARAFAC via Stochastic Thermodynamic Integration

Track: MLSP: Machine Learning for Signal Processing
Session: Learning Theory and Methods II
Time: Tuesday, May 14, 17:30 – 19:30
Authors: Thanh Huy Nguyen, Umut Şimşekli, Gaël Richard, Ali Taylan Cemgil

Speech enhancement with variational autoencoders and alpha-stable distributions

Track: AASP: Audio and Acoustic Signal Processing
Session: Active Noise Control, Source Separation, and System Identification
Time: Wednesday, May 15, 13:30 – 15:30
Authors: Simon Leglaive, Umut Şimşekli, Antoine Liutkus, Laurent Girin, Radu Horaud