{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:08:49Z","timestamp":1771877329034,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053887","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7034-7038","source":"Crossref","is-referenced-by-count":14,"title":["Attention-Based ASR with Lightweight and Dynamic Convolutions"],"prefix":"10.1109","author":[{"given":"Yuya","family":"Fujita","sequence":"first","affiliation":[]},{"given":"Aswin Shanmugam","family":"Subramanian","sequence":"additional","affiliation":[]},{"given":"Motoi","family":"Omachi","sequence":"additional","affiliation":[]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","first-page":"1717","article-title":"Speech dereverberation based on variancenormalized delayed linear prediction","volume":"18","author":"nakatani","year":"2010","journal-title":"IEEE Transactions on ASLP"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.11.005"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1186\/s13634-016-0306-6"},{"key":"ref30","article-title":"Spontaneous speech corpus of Japanese","author":"maekawa","year":"2000","journal-title":"Proc Second International Conference on Language Resources and Evaluation (LREC)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref12","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Advances in Neural Information Processing Systems (NIPS) 30"},{"key":"ref13","first-page":"5884","article-title":"Speech-transformer: a norecurrence sequence-to-sequence model for speech recognition","author":"dong","year":"2018","journal-title":"Proc ICASSP"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1107"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1938"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref18","first-page":"1243","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"2017","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref19","author":"sifre","year":"2014","journal-title":"Rigid-motion scattering for image classification"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-84"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"939","DOI":"10.21437\/Interspeech.2017-233","article-title":"A comparison of sequence-to-sequence models for speech recognition","author":"prabhavalkar","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref27","first-page":"933","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"2017","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref3","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"amodei","year":"2016","journal-title":"Proc of the 33rd International Conference on International Conference on Machine Learning (ICML)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1616"},{"key":"ref29","article-title":"LSTM time and frequency recurrence for automatic speech recognition","author":"li","year":"2015","journal-title":"Proc IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1780"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref9","first-page":"5206","article-title":"Librispeech: An asr corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"Proc ICASSP"},{"key":"ref1","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc Advances in Neural Information Processing Systems (NIPS) 28"},{"key":"ref20","article-title":"Pay less attention with lightweight and dynamic convolutions","author":"wu","year":"2019","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953077"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref24","article-title":"Fully convolutional speech recognition","author":"zeghidour","year":"2018","journal-title":"arXiv preprint arXiv 1812 02588"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1446"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2460"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1819"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053887.pdf?arnumber=9053887","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:08:59Z","timestamp":1656374939000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053887\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053887","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}