{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T18:26:10Z","timestamp":1780943170727,"version":"3.54.1"},"reference-count":30,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462430","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T18:24:48Z","timestamp":1537554288000},"page":"5389-5393","source":"Crossref","is-referenced-by-count":28,"title":["Deep Learning Based Speech Beamforming"],"prefix":"10.1109","author":[{"given":"Kaizhi","family":"Qian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiyu","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuesong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dinei","family":"Florencio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Hasegawa-Johnson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref30","first-page":"2416","article-title":"CrowdMOS: An approach for crowdsourcing mean opinion score studies","author":"flavio","year":"2011","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref10","first-page":"577","article-title":"Discriminatively trained recurrent neural networks for single-channel speech separation","author":"felix","year":"2014","journal-title":"IEEE Global Conference on Signal and Information Processing (GlobalSIP)"},{"key":"ref11","first-page":"2013","article-title":"Speech enhancement using Bayesian Wavenet","author":"kaizhi","year":"2017","journal-title":"InterSpeech"},{"key":"ref12","author":"dario","year":"2017","journal-title":"A Wavenet for speech denoising"},{"key":"ref13","author":"santiago","year":"2017","journal-title":"Segan Speech enhancement generative adversarial network"},{"key":"ref14","first-page":"196","article-title":"Neural network based spectral mask estimation for acoustic beamforming","author":"jahn","year":"2016","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref15","first-page":"1981","article-title":"Improved MVDR beamforming using single-channel mask prediction networks","author":"hakan","year":"2016","journal-title":"InterSpeech"},{"key":"ref16","first-page":"3246","article-title":"On time-frequency mask estimation for MVDR beamforming with application in robust speech recognition","author":"xiong","year":"2017","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref17","first-page":"27h-2ro","article-title":"A speech enhancement algorithm by iterating single-and multimicrophone processing and its application to robust ASR","author":"xueliang","year":"2017","journal-title":"IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref18","first-page":"66","article-title":"DNN-based speech mask estimation for eigenvector beamforming","author":"lukas","year":"2017","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref19","author":"aaron van den","year":"2016","journal-title":"WaveNet A Generative Model for Raw Audio"},{"key":"ref28","year":"2017","journal-title":"FreeSFX"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"994","DOI":"10.1109\/TASL.2009.2015090","article-title":"Beamforming with a maximum negentropy criterion","volume":"17","author":"kenichi","year":"2009","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref27","volume":"93","author":"john","year":"1993","journal-title":"DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM NIST speech disc 1–1 1"},{"key":"ref3","first-page":"3701","article-title":"Speech dereverberation via maximum-kurtosis subband adaptive filtering","volume":"6","author":"bradford","year":"2001","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"1626","DOI":"10.1109\/TASLP.2016.2577880","article-title":"Determined blind source separation unifying independent vector analysis and nonnegative matrix factorization","volume":"24","author":"daichi","year":"2016","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1109\/TAP.1982.1142739","article-title":"An alternative approach to linearly constrained adaptive beamforming","volume":"30","author":"lloyd","year":"1982","journal-title":"IEEE Transactions on Antennas and Propagation"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1109\/TASL.2006.872618","article-title":"Blind source separation exploiting higher-order frequency dependencies","volume":"15","author":"taesu","year":"2007","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref8","first-page":"3314","article-title":"Long short-term memory for speaker generalization in supervised speech separation","author":"jitong","year":"2016","journal-title":"InterSpeech"},{"key":"ref7","first-page":"2675","article-title":"Glottal model based speech beamforming for ad-hoc micro-rihone arravs","author":"yang","year":"2017","journal-title":"TNTFRSPFFrH"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1016\/j.sigpro.2014.07.014","article-title":"Optimal distributed minimum-variance beamforming approaches for speech enhancement in wireless acoustic sensor networks","volume":"107","author":"shmulik","year":"2015","journal-title":"Signal Processing"},{"key":"ref9","first-page":"1562","article-title":"Deep learning for monaural speech separation","author":"po-sen","year":"2014","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref1","author":"michael","year":"2013","journal-title":"Microphone Arrays Signal Processing Techniques and Applications"},{"key":"ref20","volume":"7","author":"norbert","year":"1949","journal-title":"Extrapolation Interpolation and Smoothing of Stationary Time Series"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"1429","DOI":"10.1109\/TASL.2009.2035038","article-title":"Diffuse reverberation model for efficient image-source simulation of room impulse responses","volume":"18","author":"eric","year":"2010","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1121\/1.382599","article-title":"Image method for efficiently simulating small-room acoustics","volume":"65","author":"jont","year":"1979","journal-title":"The Journal of the Acoustical Society of America"},{"key":"ref24","article-title":"Speech enhancement in multiple-noise conditions using deep neural networks","author":"anurag","year":"2016","journal-title":"TERSPEECH"},{"key":"ref23","author":"junichi","year":"0","journal-title":"English multi-speaker corpus for cstr voice cloning toolkit"},{"key":"ref26","author":"guoning","year":"2015","journal-title":"100 Nonspeech Sounds"},{"key":"ref25","year":"2015","journal-title":"Freesound"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Calgary, AB","start":{"date-parts":[[2018,4,15]]},"end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08462430.pdf?arnumber=8462430","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T01:18:34Z","timestamp":1598231914000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462430\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462430","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}