Double-attention mechanism of sequence-to-sequence deep neural networks for automatic speech recognition
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yook, Dongsuk | - |
dc.contributor.author | Lim, Dan | - |
dc.contributor.author | Yoo, In-Chul | - |
dc.date.accessioned | 2021-08-31T16:09:55Z | - |
dc.date.available | 2021-08-31T16:09:55Z | - |
dc.date.created | 2021-06-18 | - |
dc.date.issued | 2020 | - |
dc.identifier.issn | 1225-4428 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/59027 | - |
dc.description.abstract | Sequence-to-sequence deep neural networks with attention mechanisms have shown superior performance across various domains, where the sizes of the input and the output sequences may differ. However, if the input sequences are much longer than the output sequences, and the characteristic of the input sequence changes within a single output token, the conventional attention mechanisms are inappropriate, because only a single context vector is used for each output token. In this paper, we propose a double-attention mechanism to handle this problem by using two context vectors that cover the left and the right parts of the input focus separately. The effectiveness of the proposed method is evaluated using speech recognition experiments on the TIMIT corpus. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | ACOUSTICAL SOC KOREA | - |
dc.title | Double-attention mechanism of sequence-to-sequence deep neural networks for automatic speech recognition | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Yook, Dongsuk | - |
dc.identifier.doi | 10.7776/ASK.2020.39.5.476 | - |
dc.identifier.scopusid | 2-s2.0-85099506852 | - |
dc.identifier.wosid | 000594710300013 | - |
dc.identifier.bibliographicCitation | JOURNAL OF THE ACOUSTICAL SOCIETY OF KOREA, v.39, no.5, pp.476 - 482 | - |
dc.relation.isPartOf | JOURNAL OF THE ACOUSTICAL SOCIETY OF KOREA | - |
dc.citation.title | JOURNAL OF THE ACOUSTICAL SOCIETY OF KOREA | - |
dc.citation.volume | 39 | - |
dc.citation.number | 5 | - |
dc.citation.startPage | 476 | - |
dc.citation.endPage | 482 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.identifier.kciid | ART002628954 | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scopus | - |
dc.description.journalRegisteredClass | kci | - |
dc.relation.journalResearchArea | Acoustics | - |
dc.relation.journalWebOfScienceCategory | Acoustics | - |
dc.subject.keywordAuthor | Attention | - |
dc.subject.keywordAuthor | Sequence-to-sequence | - |
dc.subject.keywordAuthor | Deep neural network | - |
dc.subject.keywordAuthor | Automatic speech recognition | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
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.