{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T01:10:29Z","timestamp":1718327429421},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2016,6,1]],"date-time":"2016-06-01T00:00:00Z","timestamp":1464739200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2016,6]]},"DOI":"10.1109\/taslp.2016.2522646","type":"journal-article","created":{"date-parts":[[2016,1,27]],"date-time":"2016-01-27T19:12:30Z","timestamp":1453921950000},"page":"1006-1019","source":"Crossref","is-referenced-by-count":5,"title":["Feature Adaptation Using Linear Spectro-Temporal Transform for Robust Speech Recognition"],"prefix":"10.1109","volume":"24","author":[{"given":"Duc Hoang Ha","family":"Nguyen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiong","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eng Siong","family":"Chng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","first-page":"773","article-title":"Robust feature space adaptation for telephony speech recognition","author":"lei","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/89.848223"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607807"},{"key":"ref70","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum likelihood from incomplete data via the EM algorithm","volume":"39","author":"dempster","year":"1977","journal-title":"J Roy Statist Soc Series B (Methodol )"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23538-2_24"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.675369"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.940837"},{"key":"ref39","first-page":"876","article-title":"Attribute-based histogram equalization (HEQ) and its adaptation for robust speech recognition","author":"xiao","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref75","first-page":"1417","article-title":"Incremental on-line feature space MLLR adaptation for telephony speech recognition","author":"li","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2199485"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701894"},{"key":"ref79","first-page":"81","article-title":"WSJCAM0: A British English speech corpus for large vocabulary continuous speech recognition","author":"robinson","year":"0","journal-title":"Proc Int Conf Acoust Speech Signal Process (ICASSP’95)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639204"},{"key":"ref32","author":"li","year":"2015","journal-title":"Robust Automatic Speech Recognition—A Bridge to Practical Applications"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2304637"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205029"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2006.884903"},{"key":"ref36","first-page":"693","article-title":"Feature normalization using structured full transforms for robust speech recognition","author":"xiao","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1109\/TASL.2008.2006575","article-title":"Higher order cepstral moment normalization for improved robust speech recognition","volume":"17","author":"hsu","year":"2009","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1049\/el:19990215"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2329237"},{"key":"ref62","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1109\/TASLP.2014.2364452","article-title":"A regression approach to speech enhancement based on deep neural networks","volume":"23","author":"xu","year":"2015","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref61","first-page":"616","article-title":"Robust speech recognition with speech enhanced deep neural networks","author":"du","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref63","article-title":"The NTU-ADSC systems for reverberation challenge 2014","author":"xiao","year":"0","journal-title":"Reverb Challenge Workshop"},{"key":"ref28","first-page":"1367","article-title":"Compensation for the effect of the communication channel in auditory-like analysis of speech (RASTA-PLP)","author":"hermansky","year":"0","journal-title":"Proc Eur Conf Speech Commun Technol"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2013.02.050"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/89.326616"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.940833"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00061-2"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/89.466659"},{"key":"ref67","author":"papoulis","year":"2002","journal-title":"Probability random variables and stochastic processes"},{"key":"ref68","first-page":"1977","article-title":"An architecture for rapid decoding of large vocabulary conversational speech","author":"saon","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/BF01589116"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref1","author":"huang","year":"2001","journal-title":"Spoken Language Processing A Guide to Theory Algorithm and System Development"},{"key":"ref20","first-page":"45","article-title":"Robust speech dereverberation based on non-negativity and sparse nature of speech spectrograms","author":"kameoka","year":"0","journal-title":"Proc Int Conf Acoust Speech Signal Process (ICASSP’09)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947601"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2051271"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1121\/1.1914702"},{"key":"ref23","first-page":"806","article-title":"Large-vocabulary speech recognition under adverse acoustic environment","author":"deng","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198866"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00033-8"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2009015"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.201400998"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2014.01.001"},{"key":"ref58","first-page":"22","article-title":"Recurrent neural networks for noise reduction in robust ASR","author":"maas","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1994.389267"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2329190"},{"key":"ref54","first-page":"25","article-title":"Improving word accuracy with gabor feature extraction","author":"kleinschmidt","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1121\/1.1945807"},{"key":"ref52","doi-asserted-by":"crossref","first-page":"2315","DOI":"10.1523\/JNEUROSCI.20-06-02315.2000","article-title":"Spectral-temporal receptive fields of nonlinear auditory neurons obtained using natural sounds","volume":"20","author":"theunissen","year":"2000","journal-title":"J Neurosci"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2011.5942377"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2009.02.001"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.940833"},{"key":"ref12","first-page":"869","article-title":"HMM adaptation using vector Taylor series for noisy speech recognition","author":"acero","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"1586","DOI":"10.1109\/PROC.1979.11540","article-title":"enhancement and bandwidth compression of noisy speech","volume":"67","author":"lim","year":"1979","journal-title":"Proceedings of the IEEE"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"ref82","article-title":"Lasso model adaptation for automatic speech recognition","author":"li","year":"0","journal-title":"Proc ICML Workshop Learn Archit Represent Optim Speech Visual Inf Process"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1985.1164550"},{"key":"ref81","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc IEEE Workshop Autom Speech Recog and Understanding"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198871"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.815522"},{"key":"ref83","first-page":"742","article-title":"Fast speaker adaptation using eigenspace-based maximum likelihood linear regression","author":"chen","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052251"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2005.1566470"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0043"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/89.279278"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/89.906001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1995.0010"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0181"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/89.917687"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288876"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1109\/TSA.1996.481449","article-title":"Signal bias removal by maximum likelihood estimation for robust telephone speech recognition","volume":"4","author":"rahim","year":"1996","journal-title":"IEEE Trans Speech Audio Process"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1121\/1.408467"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1121\/1.392224"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1121\/1.426895"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(99)00002-3"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.876717"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/89.496215"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1121\/1.1913632"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2002082"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7463555\/07393796.pdf?arnumber=7393796","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T00:30:23Z","timestamp":1718325023000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7393796\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,6]]},"references-count":83,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2016.2522646","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,6]]}}}