Language-specific phonetic realisation of stop voicing contrasts in English and Japanese synthesised speech
JASA Express Letters · 2025
DOI: 10.1121/10.0039066 ↗Kurz gefasst
Fachartikel in der Zeitschrift JASA Express Letters, 2025. Verfasst von James Tanner und 2 weiteren Autor:innen. Beteiligte Einrichtung: English Language and Linguistics, University of Glasgow, Glasgow, G12 8QQ, United Kingdom. Hauptthemen laut MEDLINE: Language, Phonetics, Speech. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: British Academy.
Abstract (Originalsprache)
Speech synthesis has improved dramatically over recent years, enabled by large datasets and advances in neural network architectures. Little is known, however, about how synthesised speech patterns are realized from a phonetic perspective. By synthesising speech in two languages with differing implementations of stop voicing, we observe that synthesised speech broadly follows expected patterns for each language, though partially diverges for specific segments. Synthesising speakers into the opposing language also results in stops similar to target language distributions. These findings demonstrate the capability of speech synthesis models to encode phonetic information and further motivate questions regarding the phonetics of synthesised speech.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- English Language and Linguistics, University of Glasgow, Glasgow, G12 8QQ, United Kingdom.
- Faculty of Commerce, Waseda University, Tokyo, 169-8050, Japanjames.tanner@glasgow.ac.uk, y.shinohara@waseda.jp, faith.chiu@glasgow.ac.uk.
ORCID-Profile: James Tanner, Yasuaki Shinohara, Faith Chiu
Förderung
- British Academy
Zitieren
APA
Tanner, J., Shinohara, Y., & Chiu, F. (2025). Language-specific phonetic realisation of stop voicing contrasts in English and Japanese synthesised speech. JASA Express Letters. https://doi.org/10.1121/10.0039066
Vancouver
Tanner J, Shinohara Y, Chiu F. Language-specific phonetic realisation of stop voicing contrasts in English and Japanese synthesised speech. JASA Express Letters. 2025. doi:10.1121/10.0039066
BibTeX
@article{Tanner2025,
author = {Tanner, James and Shinohara, Yasuaki and Chiu, Faith},
title = {Language-specific phonetic realisation of stop voicing contrasts in English and Japanese synthesised speech},
journal = {JASA Express Letters},
year = {2025},
doi = {10.1121/10.0039066}
}
EUVIMED