Speaking Style Conversion in the Waveform Domain Using Discrete Self-Supervised Units

Gallil Maimon, Yossi Adi


Abstract
We introduce DISSC, a novel, lightweight method that converts the rhythm, pitch contour and timbre of a recording to a target speaker in a textless manner. Unlike DISSC, most voice conversion (VC) methods focus primarily on timbre, and ignore people’s unique speaking style (prosody). The proposed approach uses a pretrained, self-supervised model for encoding speech to discrete units, which makes it simple, effective, and fast to train. All conversion modules are only trained on reconstruction like tasks, thus suitable for any-to-many VC with no paired data. We introduce a suite of quantitative and qualitative evaluation metrics for this setup, and empirically demonstrate that DISSC significantly outperforms the evaluated baselines. Code and samples are available at https://pages.cs.huji.ac.il/adiyoss-lab/dissc/.
Anthology ID:
2023.findings-emnlp.541
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8048–8061
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.541
DOI:
10.18653/v1/2023.findings-emnlp.541
Bibkey:
Cite (ACL):
Gallil Maimon and Yossi Adi. 2023. Speaking Style Conversion in the Waveform Domain Using Discrete Self-Supervised Units. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 8048–8061, Singapore. Association for Computational Linguistics.
Cite (Informal):
Speaking Style Conversion in the Waveform Domain Using Discrete Self-Supervised Units (Maimon & Adi, Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2023.findings-emnlp.541.pdf