Dysarthric Speech Enhancement Based on Convolution Neural Network

Syu Siang Wang, Yu Tsao, Wei Zhong Zheng, Hsiu Wei Yeh, Pei Chun Li, Shih Hau Fang, Ying Hui Lai

研究成果: Conference contribution同行評審

摘要

Generally, those patients with dysarthria utter a distorted sound and the restrained intelligibility of a speech for both human and machine. To enhance the intelligibility of dysarthric speech, we applied a deep learning-based speech enhancement (SE) system in this task. Conventional SE approaches are used for shrinking noise components from the noise-corrupted input, and thus improve the sound quality and intelligibility simultaneously. In this study, we are focusing on reconstructing the severely distorted signal from the dysarthric speech for improving intelligibility. The proposed SE system prepares a convolutional neural network (CNN) model in the training phase, which is then used to process the dysarthric speech in the testing phase. During training, paired dysarthric-normal speech utterances are required. We adopt a dynamic time warping technique to align the dysarthric-normal utter-ances. The gained training data are used to train a CNN - based SE model. The proposed SE system is evaluated on the Google automatic speech recognition (ASR) system and a subjective listening test. The results showed that the proposed method could notably enhance the recognition performance for more than 10% in each of ASR and human recognitions from the unprocessed dysarthric speech.

原文English
主出版物標題44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022
發行者Institute of Electrical and Electronics Engineers Inc.
頁面60-64
頁數5
ISBN(電子)9781728127828
DOIs
出版狀態Published - 2022
事件44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022 - Glasgow, United Kingdom
持續時間: 11 7月 202215 7月 2022

出版系列

名字Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
2022-July
ISSN(列印)1557-170X

Conference

Conference44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022
國家/地區United Kingdom
城市Glasgow
期間11/07/2215/07/22

指紋

深入研究「Dysarthric Speech Enhancement Based on Convolution Neural Network」主題。共同形成了獨特的指紋。

引用此