Correlation distance skip connection denoising autoencoder (CDSK-DAE) for speech feature enhancement
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Badi, Alzahra | - |
dc.contributor.author | Park, Sangwook | - |
dc.contributor.author | Han, David K. | - |
dc.contributor.author | Ko, Hanseok | - |
dc.date.accessioned | 2021-08-30T22:21:52Z | - |
dc.date.available | 2021-08-30T22:21:52Z | - |
dc.date.created | 2021-06-18 | - |
dc.date.issued | 2020-06 | - |
dc.identifier.issn | 0003-682X | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/55517 | - |
dc.description.abstract | Performance of learning based Automatic Speech Recognition (ASR) is susceptible to noise, especially when it is introduced in the testing data while not presented in the training data. This work focuses on a feature enhancement for noise robust end-to-end ASR system by introducing a novel variant of denoising autoencoder (DAE). The proposed method uses skip connections in both encoder and decoder sides by passing speech information of the target frame from input to the model. It also uses a new objective function in training model that uses a correlation distance measure in penalty terms by measuring dependency of the latent target features and the model (latent features and enhanced features obtained from the DAE). Performance of the proposed method was compared against a conventional model and a state of the art model under both seen and unseen noisy environments of 7 different types of background noise with different SNR levels (0, 5, 10 and 20 dB). The proposed method also is tested using linear and non-linear penalty terms as well, where, they both show an improvement on the overall average WER under noisy conditions both seen and unseen in comparison to the state-of-the-art model. (C) 2020 Elsevier Ltd. All rights reserved. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | ELSEVIER SCI LTD | - |
dc.title | Correlation distance skip connection denoising autoencoder (CDSK-DAE) for speech feature enhancement | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Ko, Hanseok | - |
dc.identifier.doi | 10.1016/j.apacoust.2020.107213 | - |
dc.identifier.scopusid | 2-s2.0-85078119404 | - |
dc.identifier.wosid | 000521507200002 | - |
dc.identifier.bibliographicCitation | APPLIED ACOUSTICS, v.163 | - |
dc.relation.isPartOf | APPLIED ACOUSTICS | - |
dc.citation.title | APPLIED ACOUSTICS | - |
dc.citation.volume | 163 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Acoustics | - |
dc.relation.journalWebOfScienceCategory | Acoustics | - |
dc.subject.keywordAuthor | Skip connection Denoising Autoencoder (SK-DAE) | - |
dc.subject.keywordAuthor | Correlation distance measure (CDM) | - |
dc.subject.keywordAuthor | Automatic speech recognition (ASR) | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
145 Anam-ro, Seongbuk-gu, Seoul, 02841, Korea+82-2-3290-2963
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.