Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision

Eugene Kharitonov, Damien Vincent, Zalán Borsos, Raphaël Marinier, Sertan Girgin, Olivier Pietquin, Matt Sharifi, Marco Tagliasacchi, Neil Zeghidour

Abstract
We introduce SPEAR-TTS, a multi-speaker text-to-speech (TTS) system that can be trained with minimal supervision. By combining two types of discrete speech representations, we cast TTS as a composition of two sequence-to-sequence tasks: from text to high-level semantic tokens (akin to “reading”) and from semantic tokens to low-level acoustic tokens (“speaking”). Decoupling these two tasks enables training of the “speaking” module using abundant audio-only data, and unlocks the highly efficient combination of pretraining and backtranslation to reduce the need for parallel data when training the “reading” component. To control the speaker identity, we adopt example prompting, which allows SPEAR-TTS to generalize to unseen speakers using only a short sample of 3 seconds, without any explicit speaker representation or speaker labels. Our experiments demonstrate that SPEAR-TTS achieves a character error rate that is competitive with state-of-the-art methods using only 15 minutes of parallel data, while matching ground-truth speech in naturalness and acoustic quality.
Anthology ID:
2023.tacl-1.95
Volume:
Transactions of the Association for Computational Linguistics, Volume 11
Month:
Year:
2023
Address:
Cambridge, MA
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
1703–1718
Language:
URL:
https://aclanthology.org/2023.tacl-1.95
DOI:
10.1162/tacl_a_00618
Bibkey:
Cite (ACL):
Eugene Kharitonov, Damien Vincent, Zalán Borsos, Raphaël Marinier, Sertan Girgin, Olivier Pietquin, Matt Sharifi, Marco Tagliasacchi, and Neil Zeghidour. 2023. Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision. Transactions of the Association for Computational Linguistics, 11:1703–1718.
Cite (Informal):
Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision (Kharitonov et al., TACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/corrections-2024-05/2023.tacl-1.95.pdf
PDF Search