Sorry, you need to enable JavaScript to visit this website.

END-TO-END ARTICULATORY MODELING FOR DYSARTHRIC ARTICULATORY ATTRIBUTE DETECTION

Citation Author(s):
Yuqin Lin, Longbiao Wang, Jianwu Dang, Sheng Li, Chenchen Ding
Submitted by:
Yuqin Lin
Last updated:
18 April 2020 - 9:23am
Document Type:
Poster
Document Year:
2020
Event:
Presenters:
Yuqin Lin
Paper Code:
4334
Categories:

Abstract

In this study, we focus on detecting articulatory attribute errors for dysarthric patients with cerebral palsy (CP) or amyotrophic lateral sclerosis (ALS). There are two major challenges for this task. The pronunciation of dysarthric patients is unclear and inaccurate, which results in poor performances of traditional automatic speech recognition (ASR) systems and traditional automatic speech attribute transcription (ASAT). In addition, the data is limited because of the difficulty of recording. This study proposes an end-to-end automatic speech attribute transcription (E2E-ASAT) method for detecting articulatory attribute errors more precisely. To use the limited data more effectively, the parameters of the acoustic model are refactored into two layers and only one layer is retrained. Our proposed method showed good performances in both ASR and articulatory attribute detection. Our
system has a potential as a rehabilitation tool.

up
0 users have voted:

Files

ICASSP2020_poster_lin.pdf

(207)