A Self-Training Approach for Whisper to Enhance Long Dysarthric Speech Recognition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Shiyao, Zhou, Jiaming, Zhao, Shiwan, Qin, Yong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908427354112000
author Wang, Shiyao
Zhou, Jiaming
Zhao, Shiwan
Qin, Yong
author_facet Wang, Shiyao
Zhou, Jiaming
Zhao, Shiwan
Qin, Yong
contents Dysarthric speech recognition (DSR) enhances the accessibility of smart devices for dysarthric speakers with limited mobility. Previously, DSR research was constrained by the fact that existing datasets typically consisted of isolated words, command phrases, and a limited number of sentences spoken by a few individuals. This constrained research to command-interaction systems and speaker adaptation. The Speech Accessibility Project (SAP) changed this by releasing a large and diverse English dysarthric dataset, leading to the SAP Challenge to build speaker- and text-independent DSR systems. We enhanced the Whisper model's performance on long dysarthric speech via a novel self-training method. This method increased training data and adapted the model to handle potentially incomplete speech segments encountered during inference. Our system achieved second place in both Word Error Rate and Semantic Score in the SAP Challenge.
format Preprint
id arxiv_https___arxiv_org_abs_2506_22810
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Self-Training Approach for Whisper to Enhance Long Dysarthric Speech Recognition
Wang, Shiyao
Zhou, Jiaming
Zhao, Shiwan
Qin, Yong
Sound
Audio and Speech Processing
Dysarthric speech recognition (DSR) enhances the accessibility of smart devices for dysarthric speakers with limited mobility. Previously, DSR research was constrained by the fact that existing datasets typically consisted of isolated words, command phrases, and a limited number of sentences spoken by a few individuals. This constrained research to command-interaction systems and speaker adaptation. The Speech Accessibility Project (SAP) changed this by releasing a large and diverse English dysarthric dataset, leading to the SAP Challenge to build speaker- and text-independent DSR systems. We enhanced the Whisper model's performance on long dysarthric speech via a novel self-training method. This method increased training data and adapted the model to handle potentially incomplete speech segments encountered during inference. Our system achieved second place in both Word Error Rate and Semantic Score in the SAP Challenge.
title A Self-Training Approach for Whisper to Enhance Long Dysarthric Speech Recognition
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2506.22810