{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:28:52Z","timestamp":1776882532934,"version":"3.51.2"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447563","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11396-11400","source":"Crossref","is-referenced-by-count":11,"title":["Automatic Channel Selection and Spatial Feature Integration for Multi-Channel Speech Recognition Across Various Array Topologies"],"prefix":"10.1109","author":[{"given":"Bingshen","family":"Mu","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengcheng","family":"Guo","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dake","family":"Guo","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Space AI, Li Auto"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"Space AI, Li Auto"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2012.10.004"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707723"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/asru.2013.6707723"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1768"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2023-1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-226"},{"key":"ref9","article-title":"Multiple-microphone robust speech recognition using decoder-based channel selection","volume-title":"Proc. SAPA workshop. ISCA","author":"Obuchi"},{"key":"ref10","article-title":"Towards microphone selection based on room impulse response energy-related measures","author":"Wolf","year":"2009"},{"key":"ref11","article-title":"Blind estimation of the coherent-to-diffuse energy ratio from noisy speech signals","volume-title":"Proc. EUSIPCO. IEEE","author":"Jeub"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.09.015"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.862090"},{"key":"ref14","article-title":"Pairwise likelihood normalizationbased channel selection for multi-microphone ASR","volume-title":"Proc. IberSPEECH","author":"Wolf"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2007-255"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-8"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414123"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-655"},{"key":"ref19","article-title":"MFCCA: Multi-Frame Cross-Channel attention for multi-speaker ASR in Multi-party meeting scenario","volume-title":"Proc. SLT. IEEE","author":"Yu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462081"},{"key":"ref21","article-title":"End-to-end multi-channel speech separation","author":"Gu","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2800"},{"key":"ref25","article-title":"The Mixer 6 corpus: Resources for cross-channel and text independent speaker recognition","volume-title":"Proc. LREC","author":"Brandschain"},{"key":"ref26","article-title":"NARA-WPE: A python package for weighted prediction error dereverberation in numpy and tensorflow for online and offline processing","volume-title":"Proc. ITG Symposium on Speech Communication.VDE\/IEEE","author":"Drude"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref30","article-title":"End-to-end integration of speech recognition, dereverberation, beamforming, and selfsupervised learning representation","volume-title":"Proc. SLT. IEEE","author":"Masuyama"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10839"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.1997.659110"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/chime.2023-3"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2023-17"},{"key":"ref38","article-title":"Regularizing and optimizing LSTM language models","author":"Merity","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10022656"},{"key":"ref40","article-title":"Zipformer: A faster and better encoder for automatic speech recognition","author":"Yao","year":"2023"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447563.pdf?arnumber=10447563","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:34:21Z","timestamp":1722573261000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447563\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447563","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}