461 citations · 1.1k across the 30 of their papers we have counts for
3 papers · 1 filter
Speech Resynthesis from Discrete Disentangled Self-Supervised Representations
Adam Polyak, Yossi Adi, Jade Copet +5
We propose using self-supervised discrete representations for the task of speech resynthesis. To generate disentangled representation, we separately extract low-bitrate representat…
Learning spectro-temporal representations of complex sounds with parameterized neural networks
Rachid Riad, Julien Karadayi, Anne-Catherine Bachoud-Lévi +1
Deep Learning models have become potential candidates for auditory neuroscience research, thanks to their recent successes on a variety of auditory tasks. Yet, these models often l…
Weakly Supervised Multi-Embeddings Learning of Acoustic Models
Gabriel Synnaeve, Emmanuel Dupoux
We trained a Siamese network with multi-task same/different information on a speech dataset, and found that it was possible to share a network for both tasks without a loss in perf…