Chia-Yuan Chang
Chia-Yuan Chang has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Alim Misbullah
APrevent Medical Ltd
1 shared publication - Guan-Min Ho
Department of Otolaryngology‐Head and Neck Surgery Mackay Memorial Hospital Taipei Taiwan
1 shared publication - Hsiu-Wei Yeh
APrevent Medical Ltd
1 shared publication - Ji-Yan Han
Department of Biomedical Engineering, National Yang Ming Chiao Tung University, No. 155, Sec. 2, Taipei 112, Taiwan
1 shared publication - Wei Chung Chu
Department of Biomedical Engineering, National Yang Ming Chiao Tung University, No. 155, Sec. 2, Taipei 112, Taiwan
1 shared publication - Wei-Zhong Zheng
Department of Biomedical Engineering, National Yang Ming Chiao Tung University, Taipei 112304, Taiwan
1 shared publication
Latest Publications
- 9 November 2024
- Published by Springer Nature
- p. 17-31
Dysarthric Speech Recognition System with Life-Long Learning Technique in Taiwanese Mandarin
- 9 November 2024
- Published by Springer Nature
- p. 17-31
Dysarthric Speech Recognition System with Life-Long Learning Technique in Taiwanese Mandarin
- Open Access
- 10 March 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (6) , 2477
A Speech Command Control-Based Recognition System for Dysarthric Patients Based on Deep Learning Technology
Voice control is an important way of controlling mobile devices; however, using it remains a challenge for dysarthric patients. Currently, there are many approaches, such as automatic speech recognition (ASR) systems, being used to help dysarthric patients control mobile devices. However, the large computation power requirement for the ASR system increases implementation costs. To alleviate this problem, this study proposed a convolution neural network (CNN) with a phonetic posteriorgram (PPG) speech feature system to recognize speech commands, called CNN–PPG; meanwhile, the CNN model with Mel-frequency cepstral coefficient (CNN–MFCC model) and ASR-based systems were used for comparison. The experiment results show that the CNN–PPG system provided 93.49% accuracy, better than the CNN–MFCC (65.67%) and ASR-based systems (89.59%). Additionally, the CNN–PPG used a smaller model size comprising only 54% parameter numbers compared with the ASR-based system; hence, the proposed system could reduce implementation costs for users. These findings suggest that the CNN–PPG system could augment a communication device to help dysarthric patients control the mobile device via speech commands in the future.
- 10 March 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (6) , 2477
Open AccessA Speech Command Control-Based Recognition System for Dysarthric Patients Based on Deep Learning Technology
Voice control is an important way of controlling mobile devices; however, using it remains a challenge for dysarthric patients. Currently, there are many approaches, such as automatic speech recognition (ASR) systems, being used to help dysarthric patients control mobile devices. However, the large computation power requirement for the ASR system increases implementation costs. To alleviate this problem, this study proposed a convolution neural network (CNN) with a phonetic posteriorgram (PPG) speech feature system to recognize speech commands, called CNN–PPG; meanwhile, the CNN model with Mel-frequency cepstral coefficient (CNN–MFCC model) and ASR-based systems were used for comparison. The experiment results show that the CNN–PPG system provided 93.49% accuracy, better than the CNN–MFCC (65.67%) and ASR-based systems (89.59%). Additionally, the CNN–PPG used a smaller model size comprising only 54% parameter numbers compared with the ASR-based system; hence, the proposed system could reduce implementation costs for users. These findings suggest that the CNN–PPG system could augment a communication device to help dysarthric patients control the mobile device via speech commands in the future.