{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T16:14:59Z","timestamp":1784996099537,"version":"3.55.0"},"reference-count":43,"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"}],"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.2017.2763455","type":"journal-article","created":{"date-parts":[[2017,10,25]],"date-time":"2017-10-25T14:06:02Z","timestamp":1508940362000},"page":"1240-1253","source":"Crossref","is-referenced-by-count":574,"title":["Hybrid CTC\/Attention Architecture for End-to-End Speech Recognition"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5970-8631","authenticated-orcid":false,"given":"Shinji","family":"Watanabe","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4560-8039","authenticated-orcid":false,"given":"Takaaki","family":"Hori","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6822-337X","authenticated-orcid":false,"given":"Suyoun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John R.","family":"Hershey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8782-4093","authenticated-orcid":false,"given":"Tomoki","family":"Hayashi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref38","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","volume":"ldc94s13a","author":"consortium","year":"1994","journal-title":"CSR-II (WSJ1) Complete"},{"key":"ref32","article-title":"Supervised sequence labelling with recurrent neural networks","author":"graves","year":"2008"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-71"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/11939993_73"},{"key":"ref36","first-page":"947","article-title":"Spontaneous speech corpus of Japanese","volume":"2","author":"maekawa","year":"2000","journal-title":"Proc Int Conf Lang Resour Eval"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.11.005"},{"key":"ref34","volume":"ldc93s6a","author":"garofalo","year":"2007","journal-title":"CSR-I (WSJ0) Complete"},{"key":"ref10","first-page":"4960","article-title":"Listen, attend and spell","author":"chan","year":"2016","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref40","first-page":"155","article-title":"Kaldi recipe for Japanese spontaneous speech recognition and its evaluation","author":"moriya","year":"2015","journal-title":"Proc Autumn Meet Acoust Soc Jpn"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472641"},{"key":"ref12","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref13","article-title":"Google's neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-343"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref17","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in English and Mandarin","author":"amodei","year":"2016","journal-title":"Int Conf Mach Learn"},{"key":"ref18","first-page":"3707","article-title":"Neural speech recognizer: Acoustic-to-word LSTM model for large vocabulary speech recognition","author":"soltau","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3115\/1225403.1225421"},{"key":"ref28","article-title":"Chainer: A next-generation open source framework for deep learning","author":"tokui","year":"2015","journal-title":"Proc Workshop Mach Learn Syst Annu Conf Neural Inf Process Syst"},{"key":"ref3","first-page":"230","article-title":"Applying conditional random fields to Japanese morphological analysis.","volume":"4","author":"kudo","year":"2004","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"1868","DOI":"10.21437\/Interspeech.2016-71","article-title":"Maximum a posteriori based decoding for CTC acoustic models","author":"kanda","year":"2016","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-02562-4","author":"hori","year":"2013","journal-title":"Speech Recognition Algorithms Using Weighted Finite-state Transducers"},{"key":"ref5","first-page":"269","article-title":"Finite-state transducers in language and speech processing","volume":"23","author":"mohri","year":"1997","journal-title":"Comput Linguist"},{"key":"ref29","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc IEEE Workshop Autom Speech Recognit Understanding"},{"key":"ref8","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref7","article-title":"End-to-end continuous speech recognition using attention-based recurrent nn: First results","author":"chorowski","year":"2014","journal-title":"NIPS 2014 Deep Learning Workshop"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1976.10159"},{"key":"ref9","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1048"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3210-1"},{"key":"ref21","first-page":"29","article-title":"Chinese word segmentation as character tagging","volume":"8","author":"xue","year":"2003","journal-title":"Comput Linguist Chinese Lang Process"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472152"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-595"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1296"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.21437\/Interspeech.2010-343","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707742"},{"key":"ref43","article-title":"Latent sequence decompositions","author":"chan","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/8103432\/08068205.pdf?arnumber=8068205","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,5]],"date-time":"2022-08-05T10:25:03Z","timestamp":1659695103000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8068205\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":43,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2017.2763455","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,12]]}}}