{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T01:40:58Z","timestamp":1769737258399,"version":"3.49.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-009"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-001"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Mag."],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1109\/msp.2023.3266155","type":"journal-article","created":{"date-parts":[[2023,7,20]],"date-time":"2023-07-20T18:07:49Z","timestamp":1689876469000},"page":"27-39","source":"Crossref","is-referenced-by-count":5,"title":["Twenty-Five Years of Evolution in Speech and Language Processing"],"prefix":"10.1109","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0520-6844","authenticated-orcid":false,"given":"Dong","family":"Yu","sequence":"first","affiliation":[{"name":"Tencent AI Lab, Bothell, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Gong","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science, University of Nancy I, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael Alan","family":"Picheny","sequence":"additional","affiliation":[{"name":"NYU-Courant Computer Science and the Center for Data Science, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8049-2345","authenticated-orcid":false,"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[{"name":"Google, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dilek","family":"Hakkani-T\u00fcr","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI, Sunnyvale, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rohit","family":"Prasad","sequence":"additional","affiliation":[{"name":"Amazon, Boston, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heiga","family":"Zen","sequence":"additional","affiliation":[{"name":"Google Brain team, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0167-4628","authenticated-orcid":false,"given":"Jan","family":"Skoglund","sequence":"additional","affiliation":[{"name":"Google, San Francisco, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8800-0210","authenticated-orcid":false,"given":"Jan Honza","family":"\u010cernock\u00fd","sequence":"additional","affiliation":[{"name":"Department of Computer Graphics and Multimedia, Faculty of Information Technology (FIT), Brno University of Technology (BUT), Brno, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4951-5908","authenticated-orcid":false,"given":"Luk\u00e1\u0161","family":"Burget","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology (FIT), Brno University of Technology (BUT), Brno, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdelrahman","family":"Mohamed","sequence":"additional","affiliation":[{"name":"Facebook Artificial Intelligence Research group, Meta, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1002\/9781119992691"},{"key":"ref57","article-title":"BERT for joint intent classification and slot filling","author":"chen","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2004.832812"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2383614"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.1998-68"},{"key":"ref59","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2022.emnlp-main.33","article-title":"Improving zero and few-shot generalization in dialogue through instruction tuning","author":"gupta","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607775"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413810"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref52","first-page":"556","article-title":"Algorithms for non-negative matrix factorization","volume":"13","author":"seung","year":"0","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1201\/9781420015836"},{"key":"ref55","first-page":"3846","article-title":"Unsupervised sound separation using mixture invariant training","volume":"33","author":"wisdom","year":"0","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.1996.481450"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683690"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/89.817450"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.862024"},{"key":"ref18","author":"bourlard","year":"1993","journal-title":"Connectionist Speech Recognition A Hybrid Approach"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066303"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1700814"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2237151"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-21"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2647702"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-15"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-385"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.925147"},{"key":"ref44","first-page":"127","article-title":"Speaker, environment and channel change detection and clustering via the Bayesian information criterion","volume":"8","author":"chen","year":"0","journal-title":"Proc DARPA Broadcast News Transcription Understanding Workshop"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.598807"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479684"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/5.628714"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-005-2693-4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1985.1168147"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479679"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.1992-125"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1202292"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2359987"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref30","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596257"},{"key":"ref1","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref38","article-title":"Char2Wav: End-to-end speech synthesis","author":"sotelo","year":"0","journal-title":"Proc ICLR Workshop"},{"key":"ref24","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","author":"kim","year":"0","journal-title":"Proc 38th Int Conf Mach Learn (ICML)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5087\/dad.2017.102"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref25","article-title":"Do deep nets really need to be deep?","volume":"27","author":"ba","year":"0","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref21","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref28","first-page":"956","article-title":"The ISO\/MPEG unified speech and audio coding standard – Consistent high quality for all content types and at all bit rates","volume":"61","author":"neuendorf","year":"2013","journal-title":"J Audio Eng Soc"},{"key":"ref27","first-page":"2672","article-title":"Generative adversarial nets","volume":"27","author":"goodfellow","year":"0","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179063"},{"key":"ref60","article-title":"GPT-4 technical report","year":"2023"}],"container-title":["IEEE Signal Processing Magazine"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/79\/10188464\/10188908.pdf?arnumber=10188908","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,17]],"date-time":"2023-12-17T13:52:24Z","timestamp":1702821144000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10188908\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7]]},"references-count":60,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/msp.2023.3266155","relation":{},"ISSN":["1053-5888","1558-0792"],"issn-type":[{"value":"1053-5888","type":"print"},{"value":"1558-0792","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7]]}}}