Dysarthric Speech Enhancement Based on Convolution Neural Network
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. Clinical Relevance- This study enhances the intelligibility and ASR accuracy from a dysarthria speech to more than 10.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2022 |
|---|---|
| Erschienen: |
2022 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:2022 |
|---|---|
| Enthalten in: |
Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference - 2022(2022) vom: 09. Juli, Seite 60-64 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Wang, Syu-Siang [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Completed 13.09.2022 Date Revised 11.10.2022 published: Print Citation Status MEDLINE |
|---|
| doi: |
10.1109/EMBC48229.2022.9871531 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM346028671 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM346028671 | ||
| 003 | DE-627 | ||
| 005 | 20231226030444.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2022 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1109/EMBC48229.2022.9871531 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1153.xml |
| 035 | |a (DE-627)NLM346028671 | ||
| 035 | |a (NLM)36085875 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Wang, Syu-Siang |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Dysarthric Speech Enhancement Based on Convolution Neural Network |
| 264 | 1 | |c 2022 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 13.09.2022 | ||
| 500 | |a Date Revised 11.10.2022 | ||
| 500 | |a published: Print | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a 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. Clinical Relevance- This study enhances the intelligibility and ASR accuracy from a dysarthria speech to more than 10 | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Research Support, Non-U.S. Gov't | |
| 700 | 1 | |a Tsao, Yu |e verfasserin |4 aut | |
| 700 | 1 | |a Zheng, Wei-Zhong |e verfasserin |4 aut | |
| 700 | 1 | |a Yeh, Hsiu-Wei |e verfasserin |4 aut | |
| 700 | 1 | |a Li, Pei-Chun |e verfasserin |4 aut | |
| 700 | 1 | |a Fang, Shih-Hau |e verfasserin |4 aut | |
| 700 | 1 | |a Lai, Ying-Hui |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference |d 2007 |g 2022(2022) vom: 09. Juli, Seite 60-64 |w (DE-627)NLM175007292 |x 2694-0604 |7 nnns |
| 773 | 1 | 8 | |g volume:2022 |g year:2022 |g day:09 |g month:07 |g pages:60-64 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1109/EMBC48229.2022.9871531 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 2022 |j 2022 |b 09 |c 07 |h 60-64 | ||