{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T11:28:52Z","timestamp":1793446132079,"version":"4.5.0"},"reference-count":65,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1109\/asru46091.2019.9004025","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T02:01:33Z","timestamp":1582250493000},"page":"8-15","source":"Crossref","is-referenced-by-count":156,"title":["A Comparison of Transformer and LSTM Encoder Decoder Models for ASR"],"prefix":"10.1109","author":[{"given":"Albert","family":"Zeyer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Parnia","family":"Bahar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazuki","family":"Irie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ralf","family":"Schluter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hermann","family":"Ney","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2702"},{"key":"ref38","author":"mohamed","year":"2019","journal-title":"Transformers with convolutional context for ASR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2225"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013159"},{"key":"ref31","article-title":"Adaptive input representations for neural language modeling","author":"baevski","year":"2019","journal-title":"ICLRE"},{"key":"ref30","article-title":"Transformer-XL: Attentive language models beyond a fixed-length context","author":"zihang","year":"2019","journal-title":"ACL"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682539"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1910"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462497"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref62","article-title":"RE-TURNN as a generic flexible neural toolkit with application to translation and speech recognition","author":"zeyer","year":"2018","journal-title":"ACL"},{"key":"ref61","first-page":"3935","article-title":"Enhancing the TED-LIUM corpus with selected data for language modeling and more TED talks","author":"rousseau","year":"2014","journal-title":"LREC"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref28","article-title":"Improving language understanding by generative pre-training","author":"radford","year":"2018","journal-title":"OpenAIRE blog"},{"key":"ref64","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref27","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume":"abs 1906 8237","author":"zhilin","year":"2019","journal-title":"CoRR"},{"key":"ref65","author":"han","year":"2018","journal-title":"The CAPIO 2017 Conversational Speech Recognition System"},{"key":"ref29","article-title":"Language models are unsupervised multitask learners","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref2","first-page":"3707","article-title":"Neural speech recognizer: Acoustic-to-word LSTM model for large vocabulary speech recognition","author":"soltau","year":"2017","journal-title":"Proc Inter-speech"},{"key":"ref1","author":"amodei","year":"2015","journal-title":"Deep speech 2 End-to-end speech recognition in english and mandarin"},{"key":"ref20","first-page":"1243","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"2017","journal-title":"Proc ICML JMLR org"},{"key":"ref22","first-page":"6000","article-title":"Attention is all you need","author":"ashish","year":"2017","journal-title":"NIPS"},{"key":"ref21","author":"jason","year":"2019","journal-title":"Jasper An end-to-end convolutional neural acoustic model"},{"key":"ref24","article-title":"A structured self-attentive sentence embedding","author":"lin","year":"2017","journal-title":"ICLRE"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1053"},{"key":"ref26","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional Transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc NAACL-HLT"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1244"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1008"},{"key":"ref51","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1296","article-title":"Advances in joint CTC-attention based end-to-end speech recognition with a deep CNN encoder and RNN-LM","author":"hori","year":"2017","journal-title":"InterSpeech"},{"key":"ref59","first-page":"5206","article-title":"LibriSpeech: an ASR corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"ICASSP"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6322"},{"key":"ref57","article-title":"A comparison of techniques for language model integration in encoder-decoder speech recognition","author":"toshniwal","year":"2018","journal-title":"Proc SLT"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.01.014"},{"key":"ref55","author":"ba","year":"2016","journal-title":"Layer normalization"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref53","article-title":"Regularizing neural networks by penalizing confident output distributions","volume":"abs 1701 6548","author":"pereyra","year":"2017","journal-title":"CoRR"},{"key":"ref52","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1109\/72.279192","article-title":"An application of recurrent nets to phone probability estimation","volume":"5","author":"anthony","year":"1994","journal-title":"IEEE Transactions on Neural Networks"},{"key":"ref11","first-page":"338","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"hasim","year":"2014","journal-title":"InterSpeech"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2460"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952599"},{"key":"ref13","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc ICLR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1616"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953077"},{"key":"ref4","author":"collobert","year":"2016","journal-title":"Wav2letter an end-to-end convnet-based speech recognition system"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"959","DOI":"10.21437\/Interspeech.2017-546","article-title":"Di-rect acoustics-to-word models for english conversational speech recognition","author":"audhkhasi","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref6","article-title":"Listen, attend and spell: A neural network for large vocabulary conversational speech recognition","author":"william","year":"2016","journal-title":"ICASSP"},{"key":"ref5","author":"chorowski","year":"2014","journal-title":"End-to-end continuous speech recognition using attention-based recurrent nn First results"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref7","first-page":"206","article-title":"Exploring neural transducers for end-to-end speech recognition","author":"battenberg","year":"2017","journal-title":"ASRU"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1780"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3210-1"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref45","author":"chen","year":"2019","journal-title":"Gmail smart compose Real-time assisted writing"},{"key":"ref48","article-title":"A comprehensive analysis on attention models","author":"zeyer","year":"2018","journal-title":"IRASL Workshop NeurIPS"},{"key":"ref47","first-page":"2337","article-title":"Efficient training of bert by progressively stacking","author":"gong","year":"2019","journal-title":"ICML"},{"key":"ref42","author":"dong","year":"2019","journal-title":"Self-attention aligner A latency-control end-to-end model for asr using self-attention network and chunk-hopping"},{"key":"ref41","first-page":"7095","article-title":"The speechtrans-former for large-scale mandarin chinese speech recognition","author":"li","year":"2019","journal-title":"ICASSP"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1008"},{"key":"ref43","article-title":"A comparison of Transformer and recurrent neural networks on multilingual neural machine translation","author":"lakew","year":"2018","journal-title":"International Conference on Computational Linguistics"}],"event":{"name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"SG, Singapore","start":{"date-parts":[[2019,12,14]]},"end":{"date-parts":[[2019,12,18]]}},"container-title":["2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8985378\/9003727\/09004025.pdf?arnumber=9004025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T10:49:24Z","timestamp":1658141364000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9004025\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/asru46091.2019.9004025","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}