{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:14:32Z","timestamp":1740100472065,"version":"3.37.3"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003711","name":"Ministry of Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003711","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,15]]},"DOI":"10.1109\/bigdata52589.2021.9671417","type":"proceedings-article","created":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T20:39:16Z","timestamp":1642106356000},"page":"4530-4536","source":"Crossref","is-referenced-by-count":0,"title":["A Re-thinking ASR Modeling Framework using Attention Mechanisms"],"prefix":"10.1109","author":[{"given":"Chih-Ying","family":"Yang","sequence":"first","affiliation":[]},{"given":"Kuan-Yu","family":"Chen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2203"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2086"},{"key":"ref33","first-page":"79","article-title":"A statistical approach to machine translation","volume":"16","author":"brown","year":"1990","journal-title":"Computational Linguistics"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2556"},{"key":"ref31","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proceedings of NIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383497"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682539"},{"key":"ref35","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv preprintarXiv 1409 0473"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511815829"},{"key":"ref28","first-page":"1784","article-title":"Deliberation networks: Sequence generation beyond one-pass decoding","author":"xia","year":"2017","journal-title":"Proceedings of NIPS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053051"},{"key":"ref29","article-title":"Nonautoregressive Deliberation-Attention based End-to-End ASR","author":"gao","year":"2021","journal-title":"Proceedings of ISCSLP"},{"key":"ref2","article-title":"Automatic speech recognition — a brief history of the technology","author":"juang","year":"2005","journal-title":"Elsevier Encyclopedia of Language and Linguistics"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1991.10484833"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1392"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003790"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639038"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref23","article-title":"Towards better decoding and language model integration in sequence to sequence models","author":"chorowski","year":"2016","journal-title":"Proceedings of Interspeech"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683745"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1290"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947611"},{"key":"ref10","article-title":"Combining Frame-Synchronous and Label-Synchronous Systems for Speech Recognition","author":"li","year":"2021","journal-title":"arXiv preprint arXiv 2107 00764"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1705"},{"key":"ref40","article-title":"BERT: Pretraining of Deep Bidirectional Transformers for Language Understanding","author":"devlin","year":"2018","journal-title":"arXiv preprint arXiv 1802 05365"},{"key":"ref12","article-title":"A neural transducer","author":"jaitly","year":"2016","journal-title":"Proceedings of NIPS"},{"key":"ref13","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proceedings of NIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1341"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054250"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053606"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"journal-title":"Speech and Language Processing An Introduction to Natural Language Processing","year":"2008","author":"jurafsky","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref8","first-page":"5884","article-title":"Speech-transformer: a no-recurrence sequence-to-sequence model for speech recognition","author":"dong","year":"2018","journal-title":"Proceedings of ICASSP"},{"key":"ref49","article-title":"AisheU-1: An open-source Mandarin speech corpus and a speech recognition baseline","author":"bu","year":"2017","journal-title":"Proceedings of O-COCOSDA"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref9","article-title":"A comparison of label-synchronous and frame-synchronous end-to-end models for speech recognition","author":"dong","year":"2020","journal-title":"arXivpreprint arXiv 2005 10113"},{"key":"ref46","article-title":"Visual Transformers: Token-based Image Representation and Processing for Computer Vision","author":"wu","year":"2020","journal-title":"arXivpreprintarXiv 2006 03677"},{"key":"ref45","article-title":"DeepViT: Towards Deeper Vision Transformer","author":"zhou","year":"2021","journal-title":"arXiv preprint arXiv 2103 11383"},{"key":"ref48","article-title":"Non-autoregressive Transformer-based End-to-end ASR using BERT","author":"yu","year":"2021","journal-title":"arXiv preprint arXiv 2104 04805"},{"key":"ref47","article-title":"Monotonic chunkwise attention","author":"chiu","year":"2017","journal-title":"arXiv preprint arXiv 1712 05382"},{"key":"ref42","article-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","author":"liu","year":"2019","journal-title":"arXiv preprint arXiv 1907 11634"},{"key":"ref41","article-title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","author":"yang","year":"2019","journal-title":"arXiv preprint arXiv 1906 10026"},{"key":"ref44","article-title":"Transformers in Vision: A Survey","author":"khan","year":"2021","journal-title":"arXiv preprint arXiv 2101 06286"},{"key":"ref43","article-title":"A Lite BERT for Self-supervised Learning of Language Representations","author":"lan","year":"2019","journal-title":"arXiv preprint arXiv 1909 11324"}],"event":{"name":"2021 IEEE International Conference on Big Data (Big Data)","start":{"date-parts":[[2021,12,15]]},"location":"Orlando, FL, USA","end":{"date-parts":[[2021,12,18]]}},"container-title":["2021 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9671263\/9671273\/09671417.pdf?arnumber=9671417","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:55:37Z","timestamp":1652201737000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9671417\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,15]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/bigdata52589.2021.9671417","relation":{},"subject":[],"published":{"date-parts":[[2021,12,15]]}}}