{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T18:04:52Z","timestamp":1765994692050,"version":"3.28.0"},"reference-count":21,"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\/icassp40776.2020.9054653","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7709-7713","source":"Crossref","is-referenced-by-count":3,"title":["Dynamic Temporal Residual Learning for Speech Recognition"],"prefix":"10.1109","author":[{"given":"Jiaqi","family":"Xie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruijie","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shanyu","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liangrui","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael T.","family":"Johnson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Qiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472641"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-24797-2","author":"graves","year":"2012","journal-title":"Supervised Sequence Labelling with Recurrent Neural Networks"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"article-title":"Towards better decoding and language model integration in sequence to sequence models","year":"2016","author":"chorowski","key":"ref13"},{"key":"ref14","first-page":"2207","article-title":"Es-pnet: End-to-end speech processing toolkit","author":"watanabe","year":"2018","journal-title":"INTER-SPEECH"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-019-00328-x"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00012"},{"key":"ref18","article-title":"DARPA TIMIT acoustic-phonetic continuous speech corpus CD-ROM. NIST speech disc 1-1.1","volume":"93","author":"garofolo","year":"1993","journal-title":"NASA"},{"article-title":"Mixup: Beyond empirical risk min-imization","year":"2017","author":"zhang","key":"ref19"},{"article-title":"Google’s neural machine translation system: Bridging the gap between human and machine translation","year":"2016","author":"wu","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016481"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-677"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461608"},{"key":"ref7","first-page":"77","article-title":"Dilated recurrent neural networks","author":"chang","year":"2017","journal-title":"NIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178839"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.94"},{"key":"ref20","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc IEEE Workshop on Automatic Speech Recognition and Understanding"},{"article-title":"ADADELTA: An Adaptive Learning Rate Method","year":"2012","author":"zeiler","key":"ref21"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","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\/09054653.pdf?arnumber=9054653","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:11:44Z","timestamp":1656375104000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054653\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054653","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}