Speech Resynthesis from Discrete Disentangled Self-Supervised Representations - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Speech Resynthesis from Discrete Disentangled Self-Supervised Representations


We propose using self-supervised discrete representations for the task of speech resynthesis. To generate disentangled representation, we separately extract low-bitrate representations for speech content, prosodic information, and speaker identity. This allows to synthesize speech in a controllable manner. We analyze various state-of-the-art, self-supervised representation learning methods and shed light on the advantages of each method while considering reconstruction quality and disentanglement properties. Specifically, we evaluate the F0 reconstruction, speaker identification performance (for both resynthesis and voice conversion), recordings' intelligibility, and overall quality using subjective human evaluation. Lastly, we demonstrate how these representations can be used for an ultra-lightweight speech codec. Using the obtained representations, we can get to a rate of 365 bits per second while providing better speech quality than the baseline methods. Audio samples can be found under the following link: speechbot.github.io/resynthesis.
Fichier principal
Vignette du fichier
2104.00355.pdf (554.53 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03329245 , version 1 (11-10-2021)



Adam Polyak, Yossi Adi, Jade Copet, Eugene Kharitonov, Kushal Lakhotia, et al.. Speech Resynthesis from Discrete Disentangled Self-Supervised Representations. INTERSPEECH 2021 - Annual Conference of the International Speech Communication Association, Aug 2021, Brno, Czech Republic. ⟨hal-03329245⟩
111 View
305 Download



Gmail Facebook X LinkedIn More