EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Speaker-dependent laser Doppler vibrometer–based voice conversion for dysarthric speech under noisy conditions

Yu-Chuan Lee iD, Wei-Zhong Zheng iD, Jia-Wei Chen iD, Yi-Hao Jiang iD, Yen-Fu Cheng iD, Ying-Hui Lai iD

JASA Express Letters · 01.03.2026 · 6 (3)

DOI: 10.1121/10.0043006 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JASA Express Letters, online erschienen am 23.03.2026. Verfasst von Yu-Chuan Lee und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan. Hauptthemen laut MEDLINE: Dysarthria, Speech Recognition Software. Die Arbeit nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science and Technology Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study proposed the integration of a laser Doppler vibrometer sensing with a Variational Inference with adversarial learning for Text-to-Speech–based voice conversion system to enhance automatic speech recognition for individuals with dysarthria in noisy environments. The proposed framework combines the noise robustness of laser Doppler vibrometer and generative modeling capabilities of Variational Inference with adversarial learning for Text-to-Speech to transform dysarthric speech into intelligible acoustic outputs. Experimental results demonstrated significant gains in automatic speech recognition accuracy compared with conventional acoustic methods, even at low signal-to-noise ratios. These findings establish a foundation for future clinical applications of augmentative and alternative communication systems.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

DysarthriaSpeech Recognition SoftwareHumansNoiseVibrationSignal-To-Noise Ratio

Autor:innen und Institutionen

  • School of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan.
  • Department of Biomedical Engineering, National Yang Ming Chiao Tung University, Taipei, Taiwan.
  • Department of Medical Research, Taipei Veterans General Hospital, Taipei, Taiwan.
  • Institute of Brain Science, National Yang Ming Chiao Tung University, Taipei, Taiwan.
  • Medical Device Innovation & Translation Center, National Yang Ming Chiao Tung University, Taipei, Taiwan.

ORCID-Profile: Yu-Chuan Lee, Wei-Zhong Zheng, Jia-Wei Chen, Yi-Hao Jiang, Yen-Fu Cheng, Ying-Hui Lai

Förderung

  • National Science and Technology Council

Zitieren

APA

Lee, Y. C., Zheng, W. Z., Chen, J. W., Jiang, Y. H., Cheng, Y. F., & Lai, Y. H. (2026). Speaker-dependent laser Doppler vibrometer–based voice conversion for dysarthric speech under noisy conditions. JASA Express Letters, 6(3). https://doi.org/10.1121/10.0043006

Vancouver

Lee YC, Zheng WZ, Chen JW, Jiang YH, Cheng YF, Lai YH. Speaker-dependent laser Doppler vibrometer–based voice conversion for dysarthric speech under noisy conditions. JASA Express Letters. 2026;6(3). doi:10.1121/10.0043006

BibTeX
@article{Lee2026,
  author = {Lee, Yu-Chuan and Zheng, Wei-Zhong and Chen, Jia-Wei and Jiang, Yi-Hao and Cheng, Yen-Fu and Lai, Ying-Hui},
  title = {Speaker-dependent laser Doppler vibrometer–based voice conversion for dysarthric speech under noisy conditions},
  journal = {JASA Express Letters},
  year = {2026},
  volume = {6},
  number = {3},
  doi = {10.1121/10.0043006}
}
Kostenlos starten →