1 |
Speech Resynthesis from Discrete Disentangled Self-Supervised Representations
|
|
|
|
In: INTERSPEECH 2021 - Annual Conference of the International Speech Communication Association ; https://hal.inria.fr/hal-03329245 ; INTERSPEECH 2021 - Annual Conference of the International Speech Communication Association, Aug 2021, Brno, Czech Republic (2021)
|
|
Abstract:
In Proceedings of Interspeech 2021 ; International audience ; 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.
|
|
Keyword:
[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]; [INFO.INFO-SD]Computer Science [cs]/Sound [cs.SD]; Self-supervised learning; Speech codec; Speech generation; Speech resynthesis
|
|
URL: https://hal.inria.fr/hal-03329245/document https://hal.inria.fr/hal-03329245 https://hal.inria.fr/hal-03329245/file/2104.00355.pdf
|
|
BASE
|
|
Hide details
|
|
2 |
On Generative Spoken Language Modeling from Raw Audio
|
|
|
|
In: EISSN: 2307-387X ; Transactions of the Association for Computational Linguistics ; https://hal.inria.fr/hal-03329219 ; Transactions of the Association for Computational Linguistics, The MIT Press, 2021 (2021)
|
|
BASE
|
|
Show details
|
|
5 |
Textless Speech Emotion Conversion using Discrete and Decomposed Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|