Improving zero-shot style transfer text-to-speech by disentangled fine-grained style modeling
JASA Express Letters · 01.03.2026 · 6 (3)
DOI: 10.1121/10.0042974 ↗Kurz gefasst
Fachartikel in der Zeitschrift JASA Express Letters, online erschienen am 10.03.2026. Verfasst von Eray Eren und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, University of California, Los Angeles, California 90095, USA. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Recent zero-shot style-transfer speech synthesis methods have shown promising results and addressed adaptation to unseen speaking styles. While most state-of-the-art methods generalize to new speakers and styles using large models or corpora, achieving similar generalization with a smaller model remains an open challenge. We propose a zero-shot method that uses the small GenerSpeech backbone plus a fine-grained style encoder. To disentangle speakers, global/fine-grained styles, and content embeddings, we introduce a mutual-information minimization loss. To further disentangle style from speaker and boost style embedding diversity, we introduce a maximum-mean-discrepancy-guided cycle consistency loss. Experimental results show the proposed method outperforms baseline zero-shot style-transfer methods (GenerSpeech, YourTTS, VALL-E-X) with a relative average style preference improvement of 31% and a 3.64 prosody prosody similarity mean opinion score on VCTK.
Autor:innen und Institutionen
- Department of Electrical and Computer Engineering, University of California, Los Angeles, California 90095, USA.
- Flawless AI, Los Angeles, California 90401, USA.
ORCID-Profile: Eray Eren, Qingju Liu, Abeer Alwan, Gaurav Bharaj
Zitieren
APA
Eren, E., Liu, Q., Alwan, A., & Bharaj, G. (2026). Improving zero-shot style transfer text-to-speech by disentangled fine-grained style modeling. JASA Express Letters, 6(3). https://doi.org/10.1121/10.0042974
Vancouver
Eren E, Liu Q, Alwan A, Bharaj G. Improving zero-shot style transfer text-to-speech by disentangled fine-grained style modeling. JASA Express Letters. 2026;6(3). doi:10.1121/10.0042974
BibTeX
@article{Eren2026,
author = {Eren, Eray and Liu, Qingju and Alwan, Abeer and Bharaj, Gaurav},
title = {Improving zero-shot style transfer text-to-speech by disentangled fine-grained style modeling},
journal = {JASA Express Letters},
year = {2026},
volume = {6},
number = {3},
doi = {10.1121/10.0042974}
}
EUVIMED