ICASSP is an international conference on acoustics, speech and signal processing. The event is organized each year by the Institute of Electrical and Electronics Engineers (IEEE). The 2020 conference will take place in Barcelona between May 4 and May 8, 2020. It will attract world-class speakers and over 3,000 participants, who will be able to attend tutorials, workshops and exhibits. In addition, the event represents a great networking opportunity for professionals from around the world.

DSAIDIS Chair researchers and PhD students will contribute to the event with their articles. They will be presenting the following projects at the conference:

Approximate Bayesian Computation with the Sliced-Wasserstein Distance
K. Nadjahi, V. De Bortoli, A. Durmus, R. Badeau, U. Şimşekli
.

Kimia Nadjahi, PhD Student with Umut Şimşekli, received on May 5th the best student paper award from Icaspp 2020.

 

Laplace state space filter with exact inference and moment matching
Julian Neri, Philippe Depalle, Roland Badeau

Probabilistic filter and smoother for variational inference of bayesian linear dynamical systems
Julian Neri, Roland Badeau, Philippe Depalle

Joint phoneme alignment and text-informed speech separation on highly corrupted speech
Kilian Schulze-Forster, Clement S. J. Doire, Gaël Richard, Roland Badeau

Speech intelligibility enhancement by equalization for in-car applications
Enguerrand Gentet, Bertrand David, Sébastien Denjean, Gaël Richard, Vincent Roussarie

Neutral to lombard speech conversion with deep learning
Enguerrand Gentet, Bertrand David, Sébastien Denjean, Gaël Richard, Vincent Roussarie

Learning to rank music tracks using triplet loss
Laure Prétet, Gaël Richard, Geoffroy Peeters

Audio-based detection of explicit content in music
Andrea Vaglio, Romain Hennequin, Manuel Moussallam, Gaël Richard, Florence d’Alché-Buc

Audio-based auto-tagging with contextual tags for music
Karim M. Ibrahim, Jimena Royo-Letelier, Elena Epure, Geoffroy Peeters, Gaël Richard

Speech-to-singing conversion in an encoder-decoder framework
Jayneel Parekh, Preeti Rao, Yi-Hsuan Yang