Skip to main navigation Skip to search Skip to main content

Abstract

This study explores personalized Mandarin ASR for the speech impaired. Sentence and short phrase tasks selected from the VoiceBank-2023 corpus are examined for amyotrophic lateral sclerosis and esophageal-speech speakers. Unadapted speaker-independent ASR model is trained with the NER-Pro corpus to serve as a pre-trained model for the followup speaker-independent and dependent models fine-tuned with the CDSD and VoiceBank-2023 corpora. Several fine-tuning strategies are investigated. Experimental results show that the adapted speaker-dependent models attain average character error rates (CERs) ranging from 6.8% (normal) to 11.9% (moderate dysarthria) and 5.9% (normal) to 12.9% (moderate) for sentence and short phrase tasks, respectively. Last, we have implemented the fine-tuning strategies on a large corpus of a hereditary spastic paraplegia patient to evaluate frequently used sentence tasks under open-set and close-set conditions, resulting in CERs of 10.8% and 3.8%, respectively.

Original languageEnglish
Title of host publication2024 14th International Symposium on Chinese Spoken Language Processing, ISCSLP 2024
EditorsYanmin Qian, Qin Jin, Zhijian Ou, Zhenhua Ling, Zhiyong Wu, Ya Li, Lei Xie, Jianhua Tao
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages21-25
Number of pages5
ISBN (Electronic)9798331516826
DOIs
Publication statusPublished - 2024
Event14th International Symposium on Chinese Spoken Language Processing, ISCSLP 2024 - Beijing, China
Duration: Nov 7 2024Nov 10 2024

Publication series

Name2024 14th International Symposium on Chinese Spoken Language Processing, ISCSLP 2024

Conference

Conference14th International Symposium on Chinese Spoken Language Processing, ISCSLP 2024
Country/TerritoryChina
CityBeijing
Period11/7/2411/10/24

Keywords

  • amyotrophic lateral sclerosis
  • dysarthria
  • esophageal speech
  • hereditary spastic paraplegia
  • Mandarin
  • speech impaired
  • speech recognition

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language
  • Signal Processing
  • Education

Fingerprint

Dive into the research topics of 'A Preliminary Study on Constructing Mandarin Personalized Speech Recognition Systems for the Speech Impaired'. Together they form a unique fingerprint.

Cite this