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

Read full text Summarise with VIRAT
Authors: Yu-Chuan Lee, Wei-Zhong Zheng, Jia-Wei Chen, Yi-Hao Jiang, Yen‐Fu Cheng, Ying-Hui Lai
Cited by: 0
References: 19

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

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.

Fields of Study & Subjects

Speech Recognition and Synthesis Voice and Speech Disorders Speech and Audio Processing

Publication details

Journal / source
JASA Express Letters
Volume
6
Issue
3
Publication date
1 March 2026
Language
EN