{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T17:17:08Z","timestamp":1782235028515,"version":"3.54.5"},"reference-count":37,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/asru.2017.8268914","type":"proceedings-article","created":{"date-parts":[[2018,1,25]],"date-time":"2018-01-25T21:43:53Z","timestamp":1516916633000},"page":"40-47","source":"Crossref","is-referenced-by-count":15,"title":["Adversarial training for data-driven speech enhancement without parallel corpus"],"prefix":"10.1109","author":[{"given":"Takuya","family":"Higuchi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keisuke","family":"Kinoshita","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc","family":"Delcroix","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomohiro","family":"Nakatani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref32","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Networks for Machine Learning"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref37","article-title":"Network in network","author":"lin","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"605","DOI":"10.21437\/Interspeech.2011-242","article-title":"Empirical evaluation and combination of advanced language modeling techniques","author":"mikolov","year":"2011","journal-title":"InterSpeech"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.21437\/Interspeech.2010-343","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"InterSpeech"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1016\/j.neunet.2014.08.005","article-title":"Deep convolutional neural networks for large-scale speech tasks","volume":"64","author":"tara","year":"2015","journal-title":"Neural Networks"},{"key":"ref10","first-page":"953","article-title":"An EM algorithm for localizing multiple sound sources in reverberant environments","author":"michael","year":"2007","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2051355"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2665341"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"ref14","first-page":"2685","article-title":"Experiments on deep learning for speech denoising","author":"liu","year":"2014","journal-title":"TERSPEECH"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2361023"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1007\/978-3-319-22482-4_11","article-title":"Speech enhancement with LSTM recurrent neural networks and its application to noise-robust ASR","author":"weninger","year":"2015","journal-title":"International Conference on Latent Variable Analysis and Signal Separation"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472934"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471664"},{"key":"ref19","first-page":"5745","article-title":"Deep beamforming networks for multi-channel speech recognition","author":"xiong","year":"2016","journal-title":"Acoustics Speech and Signal Processing (ICASSP) 2016 IEEE International Conference on"},{"key":"ref28","article-title":"Controlling speech distortion in adaptive frequency-domain principal eigenvector beamforming","author":"warsitz","year":"2006","journal-title":"Proc IWAENC 2006"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.832994"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404828"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1155\/S1110865703305104"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2003.1285860"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1972.8817"},{"key":"ref5","first-page":"556","article-title":"Algorithms for non-negative matrix factorization","author":"lee","year":"2001","journal-title":"Advances in neural information processing systems"},{"key":"ref8","first-page":"865","article-title":"Discriminative NMF and its application to single-channel source separation","author":"weninger","year":"2014","journal-title":"INTER-SPEECH"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2270369"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(98)00047-2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2004.828896"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/0471221317"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952140"},{"key":"ref22","author":"pascual","year":"0","journal-title":"Segan Speech enhancement generative adversarial network"},{"key":"ref21","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472644"},{"key":"ref23","first-page":"30","article-title":"Speaker localization and microphone spacing invariant acoustic modeling from raw multichannel waveforms","author":"sainath","year":"2015","journal-title":"Proc IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953173"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-173"}],"event":{"name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Okinawa","start":{"date-parts":[[2017,12,16]]},"end":{"date-parts":[[2017,12,20]]}},"container-title":["2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8260578\/8268903\/08268914.pdf?arnumber=8268914","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,13]],"date-time":"2022-08-13T06:15:49Z","timestamp":1660371349000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8268914\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/asru.2017.8268914","relation":{},"subject":[],"published":{"date-parts":[[2017,12]]}}}