{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:23:37Z","timestamp":1775229817438,"version":"3.50.1"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"JST ERATO","award":["JPMJER1401"],"award-info":[{"award-number":["JPMJER1401"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2019,5]]},"DOI":"10.1109\/taslp.2019.2907015","type":"journal-article","created":{"date-parts":[[2019,3,25]],"date-time":"2019-03-25T22:44:31Z","timestamp":1553553871000},"page":"960-971","source":"Crossref","is-referenced-by-count":57,"title":["Unsupervised Speech Enhancement Based on Multichannel NMF-Informed Beamforming for Noise-Robust Automatic Speech Recognition"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5389-2346","authenticated-orcid":false,"given":"Kazuki","family":"Shimada","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3934-0745","authenticated-orcid":false,"given":"Yoshiaki","family":"Bando","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masato","family":"Mimura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7098-3896","authenticated-orcid":false,"given":"Katsutoshi","family":"Itoyama","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8387-8609","authenticated-orcid":false,"given":"Kazuyoshi","family":"Yoshii","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2686-2296","authenticated-orcid":false,"given":"Tatsuya","family":"Kawahara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109382"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.laa.2003.11.019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.11.003"},{"key":"ref31","first-page":"31","article-title":"Reference microphone selection for MWF-based noise reduction using distributed microphone arrays","author":"lawin-ore","year":"0","journal-title":"Proc ITG Symposium Speech Communication"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2002.801937"},{"key":"ref37","first-page":"2461","article-title":"Coupled initialization of multi-channel non-negative matrix factorization based on spatial and spectral information","author":"tachioka","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2011.6082314"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461434"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.9734\/BJMCS\/2015\/13026"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2303576"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ISSPA.2010.5605570"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2577880"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952163"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2665341"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462642"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.11.005"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2239990"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2031510"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2789320"},{"key":"ref50","article-title":"Fast multichannel source separation based on jointly diagonalizable spatial covariance matrices","author":"sekiguchi","year":"0","journal-title":"Proc Eur Signal Process Conf"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461530"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659591"},{"key":"ref52","first-page":"1","article-title":"A variance modeling framework based on variational autoencoders for speech enhancement","author":"leglaive","year":"0","journal-title":"Proc IEEE Int Workshop Mach Learn Signal Process"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-642"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2025790"},{"key":"ref40","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc IEEE Autom Speech Recognit Understanding Workshop"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.11.003"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/53.665"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.834599"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.898454"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404828"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404833"},{"key":"ref19","first-page":"41","article-title":"Adaptive segmentation and separation of determined convolutive mixtures under dynamic conditions","author":"loesch","year":"0","journal-title":"Proc Int Conf Latent Variable Anal Signal Separat"},{"key":"ref4","first-page":"1981","article-title":"Improved MVDR beamforming using single-channel mask prediction networks","author":"erdogan","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471664"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461639"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/9781119252634.ch12"},{"key":"ref8","first-page":"2632","article-title":"Multichannel end-to-end speech recognition","volume":"70","author":"ochiai","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952756"},{"key":"ref49","article-title":"FastMNMF: Joint diagonalization based accelerated algorithms for multichannel matrix factorization","author":"ito","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2672401"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref45","article-title":"Perceptual evaluation of speech quality (PESQ), an objective method for end-to-end speech quality assessment of narrowband telephone networks and speech codecs","author":"rix","year":"2001","journal-title":"International Telecommunication Union Geneva Switzerland ITU-T Recommendation"},{"key":"ref48","first-page":"1691","article-title":"Julius—An open source real-time large vocabulary recognition engine","author":"lee","year":"0","journal-title":"Proc Eur Conf Speech Commun Technol"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1250\/ast.20.199"},{"key":"ref42","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref41","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref43","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8677301\/08673623.pdf?arnumber=8673623","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:05:12Z","timestamp":1657746312000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8673623\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":53,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2019.2907015","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,5]]}}}