{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T12:10:54Z","timestamp":1725538254048},"reference-count":30,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383621","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T16:46:54Z","timestamp":1616690814000},"page":"229-235","source":"Crossref","is-referenced-by-count":1,"title":["Two-Stage Augmentation and Adaptive CTC Fusion for Improved Robustness of Multi-Stream end-to-end ASR"],"prefix":"10.1109","author":[{"given":"Ruizhi","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gregory","family":"Sell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hynek","family":"Hermansky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Regularizing neural networks by penalizing confident output distributions","year":"2017","author":"pereyra","key":"ref30"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-5"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.1997.659110"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3088"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2959721"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682650"},{"key":"ref16","first-page":"4835","article-title":"Joint CTC-attention based end-to-end speech recognition using multi-task learning","author":"kim","year":"2017","journal-title":"Proc of ICASSP"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1296"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"article-title":"Multi-encoder multi-resolution framework for end-to-end speech recognition","year":"2018","author":"li","key":"ref19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639693"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472765"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref3","article-title":"A Practical and Efficient Multistream Framework for Noise Robust Speech Recognition","author":"reddy mallidi","year":"2018","journal-title":"Ph D thesis"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3137"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639655"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846244"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2456"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462439"},{"key":"ref2","article-title":"Coding and decoding of messages in human speech communication: Implications for machine recognition of speech","author":"hermansky","year":"2018","journal-title":"Speech Communication"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1037"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2236871"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053455"},{"key":"ref22","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc of NIPS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-731"},{"key":"ref23","article-title":"Supervised sequence labelling with recurrent neural networks","author":"graves","year":"2008","journal-title":"Ph D Dissertation"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref25","first-page":"28","article-title":"The ami meeting corpus: A pre-announcement","author":"carletta","year":"2005","journal-title":"Proc of MLMI"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2021,1,19]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,1,22]]}},"container-title":["2021 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9383468\/9383452\/09383621.pdf?arnumber=9383621","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,31]],"date-time":"2021-05-31T17:30:34Z","timestamp":1622482234000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383621\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383621","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}