{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T07:14:03Z","timestamp":1766733243242,"version":"3.28.0"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8682539","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"7115-7119","source":"Crossref","is-referenced-by-count":86,"title":["Self-attention Networks for Connectionist Temporal Classification in Speech Recognition"],"prefix":"10.1109","author":[{"given":"Julian","family":"Salazar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katrin","family":"Kirchhoff","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiheng","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref38","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"IEEE 2011 Workshop on Automatic Speech Recognition and Understanding IEEE Signal Processing Society"},{"key":"ref33","article-title":"Deep Speech: Scaling up end-to-end speech recognition","volume":"abs 1412 5567","author":"hannun","year":"2014","journal-title":"CoRR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462361"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461558"},{"key":"ref30","first-page":"939","article-title":"A comparison of sequence-to-sequence models for speech recognition","author":"prabhavalkar","year":"2017","journal-title":"Proc Conf Int Speech Comm Assoc (Interspeech)"},{"key":"ref37","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","volume":"abs 1512 1274","author":"chen","year":"2015","journal-title":"CoRR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2057"},{"key":"ref35","first-page":"4011","article-title":"Fully convolutional recurrent network for handwritten Chinese text recognition","author":"xie","year":"2016","journal-title":"Proc IEEE Int Conf Pattern Recog (ICPR)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1446"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2414"},{"key":"ref11","article-title":"Residual convolutional CTC networks for automatic speech recognition","volume":"abs 1702 7793","author":"wang","year":"2017","journal-title":"CoRR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/72.279192"},{"key":"ref13","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Adv Neural Inform Process Syst (NIPS)"},{"key":"ref14","article-title":"Neural machine translation by jointly learning to align and translate","volume":"abs 1409 473","author":"bahdanau","year":"2014","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953077"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1107"},{"key":"ref4","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc Int Conf Machine Learn (ICML)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1910"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1038"},{"key":"ref29","article-title":"Multilingual end-to-end speech recognition with a single Transformer on low-resource languages","volume":"abs 1806 5059","author":"zhou","year":"2018","journal-title":"CoRR"},{"key":"ref5","article-title":"First-pass large vocabulary continuous speech recognition using bi-directional recurrent DNNs","volume":"abs 1408 2873","author":"hannun","year":"2014","journal-title":"CoRR"},{"key":"ref8","first-page":"173","article-title":"Deep Speech 2: End-to-end speech recognition in English and Mandarin","author":"amodei","year":"2016","journal-title":"Proc Int Conf Machine Learn (ICML)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref2","first-page":"545","article-title":"Offline handwriting recognition with multidimensional recurrent neural networks","author":"graves","year":"2009","journal-title":"Proc Adv Neural Inform Process Syst (NIPS)"},{"key":"ref9","article-title":"Wav2Letter: an end-to-end ConvNet-based speech recognition system","volume":"abs 1609 3193","author":"collobert","year":"2016","journal-title":"CoRR"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1616"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1392"},{"key":"ref22","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inform Process Syst (NIPS)"},{"key":"ref21","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":"Proc Conf Int Speech Comm Assoc (Interspeech)"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1053"},{"key":"ref41","article-title":"Optimal completion distillation for sequence learning","volume":"abs 1810 1398","author":"sabour","year":"2018","journal-title":"CoRR"},{"key":"ref23","article-title":"Letter-based speech recognition with gated ConvNets","volume":"abs 1712 9444","author":"liptchinsky","year":"2017","journal-title":"CoRR"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639575"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462497"},{"article-title":"A journey to <10% word error rate","year":"2017","author":"foundation","key":"ref43"},{"key":"ref25","article-title":"DiSAN: Directional self-attention network for RNN\/CNN-free language understanding","author":"shen","year":"2018","journal-title":"Proc AAAI Conf Artif Intell (AAAI-96)"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, United Kingdom","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08682539.pdf?arnumber=8682539","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:15:06Z","timestamp":1657854906000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682539\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682539","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}