Feature enhancement of reverberant speech by distribution matching and non-negative matrix factorization

 |  Login

Show simple item record

dc.contributor Aalto-yliopisto fi
dc.contributor Aalto University en
dc.contributor.author Keronen, Sami
dc.contributor.author Kallasjoki, Heikki
dc.contributor.author Palomaki, Kalle J.
dc.contributor.author Brown, Guy J.
dc.contributor.author Gemmeke, Jort F.
dc.date.accessioned 2017-05-31T05:56:56Z
dc.date.available 2017-05-31T05:56:56Z
dc.date.issued 2015
dc.identifier.citation Keronen , S , Kallasjoki , H , Palomaki , K J , Brown , G J & Gemmeke , J F 2015 , ' Feature enhancement of reverberant speech by distribution matching and non-negative matrix factorization ' , Eurasip Journal on Advances in Signal Processing , vol. 2015 , 76 , pp. 1-14 . https://doi.org/10.1186/s13634-015-0259-1 en
dc.identifier.issn 1687-6172
dc.identifier.issn 1687-6180
dc.identifier.other PURE UUID: 08d9bec4-625b-43d4-ad59-71b82394e215
dc.identifier.other PURE ITEMURL: https://research.aalto.fi/en/publications/feature-enhancement-of-reverberant-speech-by-distribution-matching-and-nonnegative-matrix-factorization(08d9bec4-625b-43d4-ad59-71b82394e215).html
dc.identifier.other PURE FILEURL: https://research.aalto.fi/files/13003428/art_10.1186_s13634_015_0259_1.pdf
dc.identifier.uri https://aaltodoc.aalto.fi/handle/123456789/26483
dc.description.abstract This paper describes a novel two-stage dereverberation feature enhancement method for noise-robust automatic speech recognition. In the first stage, an estimate of the dereverberated speech is generated by matching the distribution of the observed reverberant speech to that of clean speech, in a decorrelated transformation domain that has a long temporal context in order to address the effects of reverberation. The second stage uses this dereverberated signal as an initial estimate within a non-negative matrix factorization framework, which jointly estimates a sparse representation of the clean speech signal and an estimate of the convolutional distortion. The proposed feature enhancement method, when used in conjunction with automatic speech recognizer back-end processing, is shown to improve the recognition performance compared to three other state-of-the-art techniques. en
dc.format.extent 1-14
dc.format.mimetype application/pdf
dc.language.iso en en
dc.relation.ispartofseries Volume 2015 en
dc.rights openAccess en
dc.subject.other 213 Electronic, automation and communications engineering, electronics en
dc.subject.other 113 Computer and information sciences en
dc.subject.other 114 Physical sciences en
dc.subject.other 111 Mathematics en
dc.title Feature enhancement of reverberant speech by distribution matching and non-negative matrix factorization en
dc.type A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä fi
dc.description.version Peer reviewed en
dc.contributor.department Department of Signal Processing and Acoustics en
dc.subject.keyword Speech dereverberation
dc.subject.keyword Feature enhancement
dc.subject.keyword Non-negative matrix factorization
dc.subject.keyword Distribution matching
dc.subject.keyword 213 Electronic, automation and communications engineering, electronics
dc.subject.keyword 113 Computer and information sciences
dc.subject.keyword 114 Physical sciences
dc.subject.keyword 111 Mathematics
dc.identifier.urn URN:NBN:fi:aalto-201705315098
dc.identifier.doi 10.1186/s13634-015-0259-1
dc.type.version publishedVersion

Files in this item

Files Size Format View

There are no open access files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search archive

Advanced Search

article-iconSubmit a publication