{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T05:34:21Z","timestamp":1775280861235,"version":"3.50.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"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":[[2018,11]]},"DOI":"10.1109\/taslp.2018.2848701","type":"journal-article","created":{"date-parts":[[2018,6,18]],"date-time":"2018-06-18T18:26:15Z","timestamp":1529346375000},"page":"1949-1961","source":"Crossref","is-referenced-by-count":26,"title":["Flat-Start Single-Stage Discriminatively Trained HMM-Based Models for ASR"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1083-6026","authenticated-orcid":false,"given":"Hossein","family":"Hadian","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8087-8889","authenticated-orcid":false,"given":"Hossein","family":"Sameti","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"Povey","sequence":"additional","affiliation":[]},{"given":"Sanjeev","family":"Khudanpur","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.879814"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0182"},{"key":"ref33","first-page":"4839","article-title":"Minimum word error rate training for\n attention-based sequence-to-sequence models","author":"prabhavalkar","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref32","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref31","first-page":"4774","article-title":"State-of-the-art speech recognition with\n sequence-to-sequence models","author":"chiu","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref30","first-page":"193","article-title":"Exploring\n architectures, data and units for streaming end-to-end speech recognition with RNN-transducer","author":"rao","year":"0","journal-title":"Proc IEEE Workshop Autom Speech Recog and Understanding"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.543193"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115863"},{"key":"ref35","first-page":"4769","article-title":"Advancing connectionist temporal classification with\n attention modeling","author":"das","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1038"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3210-1"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref20","first-page":"3104","article-title":"Sequence to\n sequence learning with neural networks","author":"sutskever","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","article-title":"End-to-end continuous speech recognition\n using attention-based recurrent NN: first results","author":"chorowski","year":"2014"},{"key":"ref21","article-title":"Neural\n machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014"},{"key":"ref24","first-page":"944","article-title":"CTC in the context of\n generalized full-sum HMM training","author":"zeyer","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref23","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012"},{"key":"ref26","first-page":"206","article-title":"Exploring neural transducers for end-to-end\n speech recognition","author":"battenberg","year":"0","journal-title":"Proc IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref25","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"0","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref50","first-page":"3586","article-title":"Audio augmentation for speech recognition","author":"ko","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref51","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition\n in English and Mandarin","author":"amodei","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref59","first-page":"523","article-title":"Towards better decoding and language model integration in sequence to sequence models","author":"chorowski","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref58","first-page":"2440","article-title":"Reverberation robust acoustic modeling\n using i-vectors with time delay neural networks","author":"peddinti","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0043"},{"key":"ref54","first-page":"6109","article-title":"Neural network language modeling with letter-based features\n and importance sampling","author":"xu","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326009"},{"key":"ref52","article-title":"Improved training for online end-to-end speech\n recognition systems","author":"kim","year":"2017"},{"key":"ref10","first-page":"2751","article-title":"Purely sequence-trained neural networks for\n ASR based on lattice-free MMI","author":"povey","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1986.1169179"},{"key":"ref40","first-page":"1468","article-title":"Fast and accurate recurrent neural network acoustic\n models for speech recognition","author":"sak","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref12","first-page":"1323","article-title":"Deep learning-based telephony speech recognition in the wild","author":"han","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref14","article-title":"Deep speech: Scaling up end-to-end speech\n recognition","author":"hannun","year":"2014"},{"key":"ref15","first-page":"604","article-title":"Acoustic modelling with CD-CTC-SMBR LSTM RNNs","author":"senior","year":"0","journal-title":"Proc IEEE Workshop Autom Speech Recognit Understanding"},{"key":"ref16","first-page":"3707","article-title":"Neural speech\n recognizer: Acoustic-to-word LSTM model for large vocabulary speech recognition","author":"soltau","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref17","first-page":"959","article-title":"Direct acoustics-to-word models for English conversational speech\n recognition","author":"audhkhasi","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268924"},{"key":"ref19","first-page":"5794","article-title":"Advancing acoustic-to-word CTC model","author":"li","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115720"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854674"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref8","first-page":"2345","article-title":"Sequence-discriminative training of deep\n neural networks","author":"vesel\u00fd","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854675"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1016\/B978-0-08-051584-7.50037-1","article-title":"Phoneme recognition using time-delay neural networks","author":"waibel","year":"1990","journal-title":"Readings in Speech Recognition"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638951"},{"key":"ref46","first-page":"1764","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc IEEE Workshop Autom Speech Recognit Understanding"},{"key":"ref45","first-page":"3935","article-title":"Enhancing the TED-LIUM corpus with selected data for language modeling and more TED talks","author":"rousseau","year":"0","journal-title":"Proc Int Conf Lang Resources Eval"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2723507"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853592"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/1075812.1075885"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8429900\/08387866.pdf?arnumber=8387866","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T12:13:07Z","timestamp":1643199187000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8387866\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":59,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2018.2848701","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,11]]}}}