{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T22:40:50Z","timestamp":1725576050582},"reference-count":50,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/slt.2018.8639587","type":"proceedings-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T23:36:34Z","timestamp":1550187394000},"page":"353-360","source":"Crossref","is-referenced-by-count":5,"title":["Improving Attention-Based End-to-End ASR Systems with Sequence-Based Loss Functions"],"prefix":"10.1109","author":[{"given":"Jia","family":"Cui","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Weng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangsen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peidong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengzhu","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Automatic differentiation in pytorch","author":"paszke","year":"2017","journal-title":"NIPS"},{"key":"ref38","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"ASRU"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855129"},{"key":"ref32","article-title":"Crosslanguage knowledge transfer using multilingual deep neural network with shared hidden layers","author":"huang","year":"2013","journal-title":"ICASSP"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639084"},{"key":"ref30","article-title":"Multi-level language modeling and decoding for open vocabulary end-to-end speech recognition","author":"hori","year":"2017","journal-title":"ASRU"},{"key":"ref37","article-title":"Attentionbased end-to-end speech recognition in mandarin","author":"shan","year":"2017","journal-title":"CoRR"},{"key":"ref36","article-title":"Google’s neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016","journal-title":"CoRR"},{"key":"ref35","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2014","journal-title":"NIPS CoRR"},{"key":"ref34","article-title":"Multilingual representations for low resource speech recognition and keyword search","author":"cui","year":"2015","journal-title":"ASRU"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1030"},{"key":"ref27","article-title":"Minimum word error rate training for attention-based sequence-tosequence models","author":"prabhavalkar","year":"2018","journal-title":"ICASSP"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"journal-title":"Statistical Methods for Speech Recognition","year":"1997","author":"jelinek","key":"ref1"},{"key":"ref20","article-title":"An online sequence-to-sequence model using partial conditioning","author":"jaitly","year":"2016","journal-title":"NIPS"},{"key":"ref22","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"ICML"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref24","article-title":"Gram-ctc: Automatic unit selection and target decomposition for sequence labelling","author":"liu","year":"2017","journal-title":"ICML"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1705","article-title":"Recurrent neural aligner: An encoder-decoder neural network model for sequence to sequence mapping","author":"sak","year":"2017","journal-title":"InterSpeech"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960445"},{"key":"ref25","article-title":"Discriminative Training for Large Vocabulary Speech Recognition","author":"povey","year":"2003","journal-title":"Ph D thesis"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953069"},{"key":"ref10","article-title":"Building competitive direct acousticsto- word models for english conversational speech recognition","author":"audhkhasi","year":"2018","journal-title":"ICASSP"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1616"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-4012"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref13","article-title":"Cold fusion: Training seq2seq models together with language models","author":"sriram","year":"2017","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-546","article-title":"Direct acoustics-to-word models for english conversational speech recognition","author":"audhkhasi","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2765834"},{"key":"ref16","article-title":"End-to-end continuous speech recognition using attention-based recurrent nn: First results","author":"chorowski","year":"2014","journal-title":"arXiv preprint arXiv 1412 1602"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472641"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639344"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1109\/MSP.2012.2205597","article-title":"Deep neural networks for acoustic modeling in speech recognition","author":"hinton","year":"2012","journal-title":"Signal Processing Magazine"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-405","article-title":"English conversational telephone speech recognition by humans and machines","author":"saon","year":"2017","journal-title":"InterSpeech"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953159"},{"key":"ref8","article-title":"Listen, attend and spell","author":"chan","year":"2015","journal-title":"CoRR"},{"key":"ref7","article-title":"Neural speech recognizer: Acoustic-to-word lstm model for large vocabulary speech recognition","author":"soltau","year":"2016","journal-title":"arXiv preprint arXiv 1610 09975"},{"key":"ref49","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-546","article-title":"Direct acoustics-to-word models for english conversational speech recognition","author":"audhkhasi","year":"2017","journal-title":"InterSpeech"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1030"},{"key":"ref45","article-title":"Audioaugmentation for speech recognition","author":"ko","year":"2015","journal-title":"InterSpeech"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472152"},{"key":"ref47","article-title":"Deep speech: Scaling up endto- end speech recognition","author":"hannun","year":"2014","journal-title":"CoRR"},{"key":"ref42","article-title":"Adadelta: An adaptive learning rate method","author":"zeiler","year":"2012","journal-title":"arXiv 1212 5701"},{"key":"ref41","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"amodei","year":"2016","journal-title":"ICML"},{"key":"ref44","article-title":"Purely sequence-trained neural networks for asr based on lattice-free mmi","author":"povey","year":"2016","journal-title":"InterSpeech"},{"key":"ref43","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ICLRE"}],"event":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2018,12,18]]},"location":"Athens, Greece","end":{"date-parts":[[2018,12,21]]}},"container-title":["2018 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8632666\/8639030\/08639587.pdf?arnumber=8639587","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T08:11:53Z","timestamp":1643271113000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8639587\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/slt.2018.8639587","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}