Acoustical Science and Technology
Online ISSN : 1347-5177
Print ISSN : 1346-3969
ISSN-L : 0369-4232
What Survives Voice Cloning? Speaker-Related Information and Acoustic Characteristics in Same-Language and Cross-Lingual Synthesis
Yasushi Tsubota
Author information
JOURNAL OPEN ACCESS Advance online publication

Article ID: e26.122

Details
Abstract

Voice cloning can retain speaker similarity without guaranteeing preservation of specific acoustic characteristics. We characterize ten Japanese speakers using natural Japanese, matched same-language synthetic Japanese, and cross-lingual synthetic English generated with CosyVoice 3. Speaker-related information was evaluated with system-aligned CAMPPlus and independent WavLM-SV embeddings, while F0 and HNR provided interpretable acoustic measures. Same-language synthesis retained strong speaker-related similarity but consistently reduced within-utterance F0 variability, while HNR changes were speaker-dependent and reproducible. Cross-lingual speaker-retention results were representation-dependent; a supplementary matched Japanese–English control using a bilingual speaker further showed feature-dependent acoustic effects across languages.

Content from these authors
© 2026 by The Acoustical Society of Japan

This article is licensed under a Creative Commons [Attribution-NoDerivatives 4.0 International] license.
https://creativecommons.org/licenses/by-nd/4.0/
Next article
feedback
Top