Show simple item record

dc.contributor.authorHimawan, Ivan
dc.contributor.authorMotlicek, Petr
dc.contributor.authorSridharan, Sridha
dc.contributor.authorDean, David
dc.contributor.authorTjondronegoro, Dian
dc.date.accessioned2020-01-14T22:47:56Z
dc.date.available2020-01-14T22:47:56Z
dc.date.issued2015
dc.identifier.isbn978-1-5108-1790-6
dc.identifier.issn2308-457X
dc.identifier.urihttp://hdl.handle.net/10072/390264
dc.description.abstractAutomatic speech recognition from multiple distant microphones poses significant challenges because of noise and reverberations. The quality of speech acquisition may vary between microphones because of movements of speakers and channel distortions. This paper proposes a channel selection approach for selecting reliable channels based on selection criterion operating in the short-term modulation spectrum domain. The proposed approach quantifies the relative strength of speech from each microphone and speech obtained from beamforming modulations. The new technique is compared experimentally in the real reverb conditions in terms of perceptual evaluation of speech quality (PESQ) measures and word error rate (WER). Overall improvement in recognition rate is observed using delay-sum and superdirective beamformers compared to the case when the channel is selected randomly using circular microphone arrays.
dc.languageEnglish
dc.publisherInternational Speech Communication Association (ISCA)
dc.publisher.urihttps://www.isca-speech.org/archive/interspeech_2015/i15_0741.html
dc.relation.ispartofconferencename16th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2015)
dc.relation.ispartofconferencetitle16th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2015)
dc.relation.ispartofdatefrom2015-09-06
dc.relation.ispartofdateto2015-09-10
dc.relation.ispartoflocationDresden, Germany
dc.relation.ispartofpagefrom741
dc.relation.ispartofpageto745
dc.subject.fieldofresearchAcoustics and Noise Control (excl. Architectural Acoustics)
dc.subject.fieldofresearchcode091301
dc.subject.keywordsScience & Technology
dc.subject.keywordsAcoustics
dc.subject.keywordsComputer Science, Interdisciplinary Applications
dc.titleChannel Selection in the Short-time Modulation Domain for Distant Speech Recognition
dc.typeConference output
dc.type.descriptionE2 - Conferences (Non Refereed)
dcterms.bibliographicCitationHimawan, I; Motlicek, P; Sridharan, S; Dean, D; Tjondronegoro, D, Channel Selection in the Short-time Modulation Domain for Distant Speech Recognition, 16th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2015), pp. 741-745
dc.date.updated2020-01-14T22:40:17Z
dc.description.versionPublished
gro.rights.copyright© 2015 ISCA and the Author(s). The attached file is reproduced here in accordance with the copyright policy of the publisher. For information about this conference please refer to the conference’s website or contact the author(s).
gro.hasfulltextFull Text
gro.griffith.authorTjondronegoro, Dian W.


Files in this item

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record