Deep Q-network-based noise suppression for robust speech recognition
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, Tae-Jun | - |
dc.contributor.author | Chang, Joon-Hyuk | - |
dc.date.accessioned | 2022-07-06T20:37:41Z | - |
dc.date.available | 2022-07-06T20:37:41Z | - |
dc.date.created | 2021-12-08 | - |
dc.date.issued | 2021-04 | - |
dc.identifier.issn | 1300-0632 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/142006 | - |
dc.description.abstract | This study develops the deep Q-network (DQN)-based noise suppression for robust speech recognition purposes under ambient noise. We thus design a reinforcement algorithm that combines DQN training with a deep neural networks (DNN) to let reinforcement learning (RL) work for complex and high dimensional environments like speech recognition. For this, we elaborate on the DQN training to choose the best action that is the quantized noise suppression gain by the observation of noisy speech signal with the rewards of DQN including both the word error rate (WER) and objective speech quality measure. Experiments demonstrate that the proposed algorithm improves speech recognition in various noisy conditions while reducing the computational burden compared to the DNN-based noise suppression method. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | Turkiye Klinikleri | - |
dc.title | Deep Q-network-based noise suppression for robust speech recognition | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Chang, Joon-Hyuk | - |
dc.identifier.doi | 10.3906/ELK-2011-144 | - |
dc.identifier.scopusid | 2-s2.0-85117153219 | - |
dc.identifier.wosid | 000703667100007 | - |
dc.identifier.bibliographicCitation | Turkish Journal of Electrical Engineering and Computer Sciences, v.25, no.9, pp.2362 - 2373 | - |
dc.relation.isPartOf | Turkish Journal of Electrical Engineering and Computer Sciences | - |
dc.citation.title | Turkish Journal of Electrical Engineering and Computer Sciences | - |
dc.citation.volume | 25 | - |
dc.citation.number | 9 | - |
dc.citation.startPage | 2362 | - |
dc.citation.endPage | 2373 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | Y | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science, Artificial Intelligence | - |
dc.relation.journalResearchArea | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Computer Science | - |
dc.relation.journalWebOfScienceCategory | Engineering | - |
dc.subject.keywordPlus | Reinforcement learning | - |
dc.subject.keywordPlus | Speech enhancement | - |
dc.subject.keywordPlus | Speech recognition | - |
dc.subject.keywordPlus | Spurious signal noise | - |
dc.subject.keywordPlus | Ambient noise | - |
dc.subject.keywordPlus | Deep Q-network | - |
dc.subject.keywordPlus | High dimensional environment | - |
dc.subject.keywordPlus | Network training | - |
dc.subject.keywordPlus | Network-based | - |
dc.subject.keywordPlus | Noise suppression | - |
dc.subject.keywordPlus | Noisy speech signals | - |
dc.subject.keywordPlus | Reinforcement algorithms | - |
dc.subject.keywordPlus | Robust speech recognition | - |
dc.subject.keywordPlus | Word error rate | - |
dc.subject.keywordAuthor | Deep neural network | - |
dc.subject.keywordAuthor | Deep Q-network | - |
dc.subject.keywordAuthor | Noise suppression | - |
dc.subject.keywordAuthor | Reinforcement learning | - |
dc.subject.keywordAuthor | Speech enhancement | - |
dc.subject.keywordAuthor | Speech recognition | - |
dc.identifier.url | https://journals.tubitak.gov.tr/elektrik/issues/elk-21-29-5/elk-29-5-7-2011-144.pdf | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
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.