{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T07:40:09Z","timestamp":1735026009474,"version":"3.32.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"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":[[2024,11,7]]},"DOI":"10.1109\/iscslp63861.2024.10800658","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"721-725","source":"Crossref","is-referenced-by-count":0,"title":["Cuside-Array: A Streaming Multi-Channel End-to-End Speech Recognition System with Realistic Evaluations"],"prefix":"10.1109","author":[{"given":"Xiangzhu","family":"Kong","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Xinjiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianqi","family":"Ning","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xinjiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xinjiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhijian","family":"Ou","sequence":"additional","affiliation":[{"name":"Tsinghua University,Speech Processing and Machine Intelligence (SPMI) Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746465"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP57327.2022.10038153"},{"key":"ref4","article-title":"Signal processing techniques and applications","volume-title":"Microphone Arrays: Signal Processing Techniques and Applications","author":"Arrays","year":"2001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471664"},{"article-title":"The THU-SPMI CHiME-4 system: Lightweight design with advanced multi-channel processing, feature enhancement, and language modeling","volume-title":"Proc. CHiME-4 Workshop","author":"Xiang","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953173"},{"article-title":"Multichannel end-to-end speech recognition","volume-title":"International conference on machine learning","author":"Ochiai","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854663"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-655"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404843"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472671"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2018.8521354"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095367"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-11214"},{"issue":"18","key":"ref16","first-page":"583","article-title":"Measuring robustness to natural distribution shifts in image classification","volume":"33","author":"Taori","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","article-title":"Robust speech recognition via large-scale weak su-pervision","volume-title":"Proc. ICML. PMLR","author":"Radford","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2016.7472778"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-173"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022715"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682954"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2732"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1693"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2539499"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2021-1397","article-title":"Aishell-4: An open source dataset for speech enhancement, separation, recognition and speaker diarization in conference scenario","volume-title":"arXiv preprint","author":"Fu","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461310"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.1109\/ASRU51503.2021.9688126","article-title":"Conferencingspeech challenge: Towards far-field multi-channel speech enhancement for video con-ferencing","volume-title":"Proc. ASRU","author":"Rao"},{"key":"ref28","article-title":"Aishell-l: An open-source mandarin speech corpus and a speech recognition base-line","volume-title":"Proc. 20th conference of the oriental chapter of the international coordinating committee on speech databases and speech I\/O systems and assessment (O-COCOSDA)","author":"Bu","year":"2017"},{"key":"ref29","article-title":"Musan: A music, speech, and noise corpus","author":"Snyder","year":"2015","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.10.005"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1989.266481"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2024,11,7]]},"location":"Beijing, China","end":{"date-parts":[[2024,11,10]]}},"container-title":["2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799944\/10799969\/10800658.pdf?arnumber=10800658","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:33:59Z","timestamp":1735022039000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800658\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800658","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}