{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T10:22:11Z","timestamp":1779358931809,"version":"3.51.4"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2018,2,1]],"date-time":"2018-02-01T00:00:00Z","timestamp":1517443200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Intelligence Advanced Research Projects Activity via Department of Defense U.S. Army Research Laboratory","award":["W911NF-12-C-0012"],"award-info":[{"award-number":["W911NF-12-C-0012"]}]},{"name":"Singapore Ministry of Education Academic Research Fund Tier 2","award":["MOE2014-T2-1-068"],"award-info":[{"award-number":["MOE2014-T2-1-068"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2018,2]]},"DOI":"10.1109\/taslp.2017.2774919","type":"journal-article","created":{"date-parts":[[2017,11,17]],"date-time":"2017-11-17T19:10:14Z","timestamp":1510945814000},"page":"256-265","source":"Crossref","is-referenced-by-count":38,"title":["Improving Interpretability and Regularization in Deep Learning"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0269-3555","authenticated-orcid":false,"given":"Chunyang","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark J. F.","family":"Gales","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anton","family":"Ragni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1939-4161","authenticated-orcid":false,"given":"Penny","family":"Karanasou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Khe Chai","family":"Sim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855129"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854049"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178960"},{"key":"ref32","article-title":"The HTK book (for HTK version 3.5)","author":"young","year":"2015"},{"key":"ref31","first-page":"5","article-title":"1997 broadcast news benchmark test\n results: English and non-English","author":"pallett","year":"0","journal-title":"Proc 1998 DARPA Broadcast News Transcription and Understanding Workshop"},{"key":"ref30","first-page":"11","article-title":"The 1996 broadcast news speech and language-model corpus","author":"graff","year":"0","journal-title":"Proceedings of the 1997 DARPA Speech Recognition Workshop"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109382"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.862024"},{"key":"ref35","first-page":"829","article-title":"Improving speech recognition and keyword search\n for low resource languages using web data","author":"mendels","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472829"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"ref40","first-page":"3660","article-title":"Joint decoding of tandem and hybrid systems for improved keyword spotting on low\n resource languages","author":"wang","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639012"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178780"},{"key":"ref13","article-title":"Mixture density networks","author":"bishop","year":"1994"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178776"},{"key":"ref15","first-page":"1","article-title":"Hybrid\n orthogonal projection and estimation (HOPE): A new framework to learn neural networks","volume":"17","author":"zhang","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178785"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472629"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/0954-1810(94)00011-S"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298640"},{"key":"ref28","article-title":"CSR-I (WSJ0) complete","author":"garofalo","year":"2007"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref27","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref6","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from\n overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref29","article-title":"The babel program and low resource speech technology","author":"harper","year":"0","journal-title":"Proc ASRU"},{"key":"ref5","article-title":"Achieving human parity in conversational\n speech recognition","author":"xiong","year":"2016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref7","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"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953074"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-580"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299155"},{"key":"ref22","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref21","article-title":"Deep\n inside convolutional networks: Visualising image classification models and saliency maps","author":"simonyan","year":"2013"},{"key":"ref42","first-page":"45","article-title":"Results of the 2006 spoken term detection\n evaluation","author":"fiscus","year":"0","journal-title":"Proc ACM SIGIR Workshop Searching Spontaneous Conversational Speech"},{"key":"ref24","first-page":"-105i","article-title":"Minimum phone error and I-smoothing for improved discriminative training","volume":"1","author":"povey","year":"0","journal-title":"Proc 2002 IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855126"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206545"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404853"},{"key":"ref43","article-title":"The development of the Cambridge University RT-04 diarisation\n system","author":"tranter","year":"0","journal-title":"Proc Fall 2004 Rich Transcription Workshop (RT-04)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078569"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8186325\/08114209.pdf?arnumber=8114209","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:24:17Z","timestamp":1642004657000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8114209\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2]]},"references-count":43,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2017.2774919","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,2]]}}}