Deep Neural Network Based Blind Estimation of Reverberation Time Based on Multi-channel Microphones
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Myungin | - |
dc.contributor.author | Chang, Joon Hyuk | - |
dc.date.accessioned | 2021-07-30T05:01:08Z | - |
dc.date.available | 2021-07-30T05:01:08Z | - |
dc.date.created | 2021-05-12 | - |
dc.date.issued | 2018-05 | - |
dc.identifier.issn | 1610-1928 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/2709 | - |
dc.description.abstract | Reverberation causes a performance degradation in distinct speech processing. For this reason, quantitatively estimating the amount of reverberation from the signal received by the microphone has been an important task for characterizing room acoustics and compensating for degradation due to an algorithm. In this paper, a novel method that estimates the reverberation time (T-60) based on multi-channel microphones using a deep neural network (DNN) is proposed. Each channel's distribution of the decay rates for each frequency and the generalized cross-correlation with phase transform (GCC-PHAT) between the microphones are adopted as the input feature vectors for DNN training. Those refined features enable the DNN composed of multiple nonlinear hidden layers to learn the nonlinear relationship that labels the reverberation time from the input features, which is known to be challenging with low-order features. The proposed algorithm is evaluated with extensive noisy conditions, and the results show the advantage of employing multi-channel signals with spatial features when compared with conventional methods. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | S HIRZEL VERLAG | - |
dc.title | Deep Neural Network Based Blind Estimation of Reverberation Time Based on Multi-channel Microphones | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Chang, Joon Hyuk | - |
dc.identifier.doi | 10.3813/AAA.919191 | - |
dc.identifier.scopusid | 2-s2.0-85047306680 | - |
dc.identifier.wosid | 000434942500011 | - |
dc.identifier.bibliographicCitation | ACTA ACUSTICA UNITED WITH ACUSTICA, v.104, no.3, pp.486 - 495 | - |
dc.relation.isPartOf | ACTA ACUSTICA UNITED WITH ACUSTICA | - |
dc.citation.title | ACTA ACUSTICA UNITED WITH ACUSTICA | - |
dc.citation.volume | 104 | - |
dc.citation.number | 3 | - |
dc.citation.startPage | 486 | - |
dc.citation.endPage | 495 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Acoustics | - |
dc.relation.journalWebOfScienceCategory | Acoustics | - |
dc.subject.keywordPlus | Architectural acoustics | - |
dc.subject.keywordPlus | Blind equalization | - |
dc.subject.keywordPlus | Decay (organic) | - |
dc.subject.keywordPlus | Microphones | - |
dc.subject.keywordPlus | Reverberation | - |
dc.subject.keywordPlus | Speech processing | - |
dc.subject.keywordPlus | Blind estimations | - |
dc.subject.keywordPlus | Conventional methods | - |
dc.subject.keywordPlus | Generalized cross correlations | - |
dc.subject.keywordPlus | Noisy conditions | - |
dc.subject.keywordPlus | Non-linear relationships | - |
dc.subject.keywordPlus | Performance degradation | - |
dc.subject.keywordPlus | Reverberation time | - |
dc.subject.keywordPlus | Spatial features | - |
dc.subject.keywordPlus | Deep neural networks | - |
dc.identifier.url | https://www.ingentaconnect.com/content/dav/aaua/2018/00000104/00000003/art00012;jsessionid=3be4qmthois6l.x-ic-live-03 | - |
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.