Fine-Tuning Automatic Speech Recognition for People with Parkinson's: An Effective Strategy for Enhancing Speech Technology Accessibility

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zheng, Xiuwen, Phukon, Bornali, Hasegawa-Johnson, Mark
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910624409190400
author Zheng, Xiuwen
Phukon, Bornali
Hasegawa-Johnson, Mark
author_facet Zheng, Xiuwen
Phukon, Bornali
Hasegawa-Johnson, Mark
contents This paper enhances dysarthric and dysphonic speech recognition by fine-tuning pretrained automatic speech recognition (ASR) models on the 2023-10-05 data package of the Speech Accessibility Project (SAP), which contains the speech of 253 people with Parkinson's disease. Experiments tested methods that have been effective for Cerebral Palsy, including the use of speaker clustering and severity-dependent models, weighted fine-tuning, and multi-task learning. Best results were obtained using a multi-task learning model, in which the ASR is trained to produce an estimate of the speaker's impairment severity as an auxiliary output. The resulting word error rates are considerably improved relative to a baseline model fine-tuned using only Librispeech data, with word error rate improvements of 37.62\% and 26.97\% compared to fine-tuning on 100h and 960h of LibriSpeech data, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2409_19818
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Fine-Tuning Automatic Speech Recognition for People with Parkinson's: An Effective Strategy for Enhancing Speech Technology Accessibility
Zheng, Xiuwen
Phukon, Bornali
Hasegawa-Johnson, Mark
Audio and Speech Processing
Sound
This paper enhances dysarthric and dysphonic speech recognition by fine-tuning pretrained automatic speech recognition (ASR) models on the 2023-10-05 data package of the Speech Accessibility Project (SAP), which contains the speech of 253 people with Parkinson's disease. Experiments tested methods that have been effective for Cerebral Palsy, including the use of speaker clustering and severity-dependent models, weighted fine-tuning, and multi-task learning. Best results were obtained using a multi-task learning model, in which the ASR is trained to produce an estimate of the speaker's impairment severity as an auxiliary output. The resulting word error rates are considerably improved relative to a baseline model fine-tuned using only Librispeech data, with word error rate improvements of 37.62\% and 26.97\% compared to fine-tuning on 100h and 960h of LibriSpeech data, respectively.
title Fine-Tuning Automatic Speech Recognition for People with Parkinson's: An Effective Strategy for Enhancing Speech Technology Accessibility
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2409.19818