Dysarthric Speech Recognition Using Pseudo-Labeling, Self-Supervised Feature Learning, and a Joint Multi-Task Learning Approach

Dysarthric Speech Recognition Using Pseudo-Labeling, Self-Supervised Feature Learning, and a Joint Multi-Task Learning Approach

In this paper, we investigate the use of the spontaneous speech of dysarthric people for training an automatic speech recognition (ASR) model for them. Although the spontaneous speech of dysarthric people can be collected relatively easily compared to script-reading speech, which is obtained by havi...

Full description

Bibliographic Details
Main Authors: Ryoichi Takashima, Yuya Sawa, Ryo Aihara, Tetsuya Takiguchi, Yoshie Imai
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Speech recognition
dysarthria
pseudo-labeling
self-supervised feature learning
Online Access:https://ieeexplore.ieee.org/document/10463016/

Internet

https://ieeexplore.ieee.org/document/10463016/

Similar Items