Exploring cross-lingual voice conversion methods for anonymizing low-resource text-to-speech

Download	View final version: Exploring cross-lingual voice conversion methods for anonymizing low-resource text-to-speech (PDF, 511 KiB)
DOI	Resolve DOI: https://doi.org/10.18653/v1/2026.eacl-short.16
Author	Search for: Wang, Shenran¹; Search for: Pine, Aidan²ORCID identifier: https://orcid.org/0000-0001-6552-5324; Search for: Geng, Mengzhe²ORCID identifier: https://orcid.org/0000-0002-7886-439X
Affiliation	University of British Columbia National Research Council Canada. Digital Technologies
Format	Text, Article
Conference	19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers), March 24-29, 2026, Rabat, Morocco
Abstract	We describe and compare multiple approaches for using voice conversion techniques to mask speaker identities in low-resource text-to-speech. We build and evaluate speaker-anonymized text-to-speech systems for two Canadian Indigenous languages, nêhiyawêwin and SENĆOŦEN, and show that cross-lingual speaker transfer via multilingual training with English data produces the most consistent results across both languages. Our research also underscores the need for better evaluation metrics tailored to cross-lingual voice conversion.
Date published	2026-03-29
Publisher	Association for Computational Linguistics
Licence	Creative Commons Attribution 4.0 International (CC BY 4.0) https://creativecommons.org/licenses/by/4.0/
In	Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics Short Papers 2 (29 March 2026): 225–231. https://doi.org/10.18653/v1/2026.eacl-short.
Language	English
Peer reviewed	Yes
Export citation	Export as RIS
Report a correction	Report a correction (opens in a new tab)
Record identifier	66e49939-2b67-4de7-9608-ee3e0d7aadcd
Record created	2026-04-16
Record modified	2026-06-03

Page details

From:

National Research Council Canada

Date modified:: 2026-06-17