{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T04:38:18Z","timestamp":1729658298294,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8461944","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"2531-2535","source":"Crossref","is-referenced-by-count":15,"title":["A Hybrid Approach to Combining Conventional and Deep Learning Techniques for Single-Channel Speech Enhancement and Recognition"],"prefix":"10.1109","author":[{"given":"Yan-Hui","family":"Tu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ivan","family":"Tashev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuayb","family":"Zarar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chin-Hui","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"1849","DOI":"10.1109\/TASLP.2014.2352935","article-title":"On training targets for supervised speech separation","volume":"22","author":"wang","year":"2014","journal-title":"IEEE Trans Audio Speech and Lang Proc"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-437"},{"key":"ref13","first-page":"643","article-title":"Learning sequential structure in simple recurrent networks","author":"servanschreiber","year":"1989","journal-title":"Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854294"},{"key":"ref15","first-page":"577","article-title":"Discriminatively trained recurrent neural networks for single-channel speech separation","author":"weninger","year":"2014","journal-title":"Proc IEEE Global Conf Signal and Information Process (GlobaISIP)"},{"key":"ref16","article-title":"A speech enhancement approach using piecewise linear approximation of an explicit model of environmental distortions","author":"du","year":"2008","journal-title":"Proc Annual Conference of International Speech Communication Association (INTERSPEECH)"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1007\/978-3-642-55016-4_12","article-title":"On the ideal ratio mask as the goal of computational auditory scene analysis","author":"hummersone","year":"2014","journal-title":"Blind Source Separation"},{"journal-title":"ITU-T Std","article-title":"Perceptual evaluation of speech quality (PESQ): an objective method for endto-end speech quality assessment of narrow-band telephone networks and speech codecs","year":"2001","key":"ref18"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"437","DOI":"10.21437\/Interspeech.2011-169","article-title":"Conversational speech transcription using context-dependent deep neural networks","author":"seide","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1109\/TASSP.1984.1164453","article-title":"Speech enhancement using a minimum-mean square error short-time spectral amplitude estimator","volume":"32","author":"ephraim","year":"1984","journal-title":"IEEE Transactions on Acoustics Speech and Signal Processing"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163394"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1002\/9780470994443"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1985.1164550"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1109\/ISCSLP.2014.6936615","article-title":"Speech separation based on improved deep neural networks with dual outputs of speech features for both target and interfering speakers","author":"tu","year":"2014","journal-title":"Proc Int Symp Chinese Spoken Language Processing (ISCSLP)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/2946.001.0001","author":"wiener","year":"1949","journal-title":"Extrapolation Interpolation and Smoothing of Stationary Time Series with Engineering Applications"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2250961"},{"key":"ref20","article-title":"An introduction to computational networks and the computational network toolkit","author":"agarwal","year":"2014","journal-title":"Microsoft Technical Report MSR-TR-2014-112 Tech Rep"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2018,4,15]]},"location":"Calgary, AB","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\/08461944.pdf?arnumber=8461944","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,2]],"date-time":"2022-09-02T10:53:17Z","timestamp":1662115997000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461944\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8461944","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}