EUVIMEDEUVIMED entdecken
Crossref

Research on speech conversion of Japanese dialects

Hewei Zhang, Daisuke Saito, Nobuaki Minematsu

The Journal of the Acoustical Society of America · 01.10.2025 · 158 (4_Supplement) · A463-A463

DOI: 10.1121/10.0041534 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, erschienen am 01.10.2025. Verfasst von Hewei Zhang und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dialect is a broad conception containing both the variation of phonology and morphology. Converting a dialect speech into standard one could make it more understandable, while the reverse could make a speech full of regional characteristic. Currently, research on dialect conversion had been taken on many languages including Mandarin, English, and Arabic. But in the case of Japanese, there are a great number of dialect that lack enough speech data for training a modern sequence-to-sequence converter. In this research, a pipeline based on pretrained LM encoder and speech-LM was proposed to perform dialect speech conversion. Furthermore, by applying finetuning, non-parallel corpus in the form of either speech or text could be utilized for training the model, greatly enlarged the scale of accessible data. Finally, different structures were implemented and tested, pointed out future directions for the research.

Zitieren

APA

Zhang, H., Saito, D., & Minematsu, N. (2025). Research on speech conversion of Japanese dialects. The Journal of the Acoustical Society of America, 158(4_Supplement), A463-A463. https://doi.org/10.1121/10.0041534

Vancouver

Zhang H, Saito D, Minematsu N. Research on speech conversion of Japanese dialects. The Journal of the Acoustical Society of America. 2025;158(4_Supplement):A463-A463. doi:10.1121/10.0041534

BibTeX
@article{Zhang2025,
  author = {Zhang, Hewei and Saito, Daisuke and Minematsu, Nobuaki},
  title = {Research on speech conversion of Japanese dialects},
  journal = {The Journal of the Acoustical Society of America},
  year = {2025},
  volume = {158},
  number = {4_Supplement},
  pages = {A463--A463},
  doi = {10.1121/10.0041534}
}
Kostenlos starten →