Work

Exploring Cross-Lingual Voice Conversion Methods for Anonymizing Low-Resource Text-to-Speech

Year: 2026

Type: conference-paper

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 SEN ĆOTEN, 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.Our code can be found at https://github.com/EveryVoiceTTS/ Speaker_Anonymization_StyleTTS2

Source: Conference of the European Chapter of the Association for Computational Linguistics

DOI: 10.18653/v1/2026.eacl-short.16

Authors: Shenran Wang, Aidan Pine, Mengzhe Geng

Institutions: University of British Columbia, National Research Council Canada

Language: English

Topic: Speech Recognition and Synthesis

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W7140133503

FWCI: 8.547

Cites:

Cited by: 1

Related to: 10