{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T14:26:33Z","timestamp":1740147993867,"version":"3.37.3"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2017,12,1]],"date-time":"2017-12-01T00:00:00Z","timestamp":1512086400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100000781","name":"European Research Council (ERC)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"name":"European Union's Horizon 2020 research and innovation program (SEQCLAS)","award":["694537"],"award-info":[{"award-number":["694537"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/jstsp.2017.2752691","type":"journal-article","created":{"date-parts":[[2017,9,14]],"date-time":"2017-09-14T18:13:48Z","timestamp":1505412828000},"page":"1265-1273","source":"Crossref","is-referenced-by-count":6,"title":["Inverted Alignments for End-to-End Automatic Speech Recognition"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0359-3027","authenticated-orcid":false,"given":"Patrick","family":"Doetsch","sequence":"first","affiliation":[]},{"given":"Mirko","family":"Hannemann","sequence":"additional","affiliation":[]},{"given":"Ralf","family":"Schluter","sequence":"additional","affiliation":[]},{"given":"Hermann","family":"Ney","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288835"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/89.536930"},{"article-title":"Sequence transduction with recurrent neural networks","year":"2012","author":"graves","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-71"},{"key":"ref31","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":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1073"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref36","article-title":"A neural transducer","volume":"abs 1511 4868","author":"jaitly","year":"2016","journal-title":"CoRR"},{"key":"ref35","article-title":"Generating sequences with recurrent neural networks","volume":"abs 1308 850","author":"graves","year":"2013","journal-title":"CoRR"},{"key":"ref34","article-title":"Sequence to\n sequence learning with neural networks","volume":"abs 1409 3215","author":"sutskever","year":"2014","journal-title":"CoRR"},{"key":"ref28","first-page":"2630","article-title":"Semi-supervised maximum mutual information training of deep neural network acoustic models","author":"manohar","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404850"},{"key":"ref29","article-title":"Connectionist speech recognition with a global MMI algorithm","author":"haffner","year":"0","journal-title":"Proc Euro Conf Speech Commun Technol"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-391"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854675"},{"key":"ref20","first-page":"3249","article-title":"A study of the recurrent neural network encoder-decoder\n for large vocabulary speech recognition","author":"lu","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638970"},{"key":"ref21","article-title":"Inverted HMM—A proof of\n concept","author":"doetsch","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225984"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1986.1164788"},{"key":"ref26","first-page":"4860","article-title":"A multi-stream ASR framework for BLSTM\n modeling of conversational speech","author":"w\u00f6llmer","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref25","article-title":"Multi-resolution RASTA filtering for TANDEM-based ASR","author":"hermansky","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref51","first-page":"39","article-title":"The RWTH\/UPB\/FORTH system combination for the\n 4th CHiME challenge evaluation","author":"menne","year":"2016","journal-title":"Proc 4th Int Workshop Speech Process Everyday Environments"},{"key":"ref53","first-page":"3281","article-title":"RASR—The RWTH Aachen University open\n source speech recognition toolkit","author":"rybach","year":"2014","journal-title":"Proc Int Conf Acoust Speech Signal Process Syst (ICASSP)"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953177"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref11","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume":"14","author":"graves","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref40","first-page":"1898","article-title":"Efficient segmental conditional random fields for phone recognition","author":"he","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref12","first-page":"173","article-title":"Deep speech: Scaling up end-to-end speech\n recognition","author":"hannun","year":"0","journal-title":"Conf Machine Learning"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178778"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref18","article-title":"End-to-end continuous speech recognition\n using attention-based recurrent NN: first results","volume":"abs 1412 1602","author":"chorowski","year":"2014","journal-title":"CoRR"},{"key":"ref19","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"journal-title":"Connectionist Speech Recognition A Hybrid Approach","year":"1993","author":"bourlard","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-595"},{"key":"ref6","article-title":"English conversational telephone speech\n recognition by humans and machines","author":"saon","year":"0","journal-title":"Proc INTERSPEECH"},{"article-title":"Achieving human parity in conversational\n speech recognition","year":"2016","author":"xiong","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.862024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.11.005"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref46","article-title":"The neural noisy channel","author":"yu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1138"},{"key":"ref48","first-page":"661","article-title":"Lattice decoding and\n rescoring with long-span neural network language models","author":"sundermeyer","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref47","article-title":"Joint CTC-attention\n based end-to-end speech recognition using multi-task learning","volume":"abs 1609 6773","author":"kim","year":"2016","journal-title":"CoRR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404845"},{"key":"ref41","article-title":"Deep segmental neural networks for speech\n recognition","author":"abdel-hamid","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-40"},{"key":"ref43","article-title":"Segmental\n recurrent neural networks","author":"kong","year":"0","journal-title":"Proc Int Conf Learn Representations"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/8103432\/08038027.pdf?arnumber=8038027","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:59:46Z","timestamp":1642006786000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8038027\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":53,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2017.2752691","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"type":"print","value":"1932-4553"},{"type":"electronic","value":"1941-0484"}],"subject":[],"published":{"date-parts":[[2017,12]]}}}