{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:30:05Z","timestamp":1776889805770,"version":"3.51.2"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746749","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7332-7336","source":"Crossref","is-referenced-by-count":22,"title":["Multi-Channel End-To-End Neural Diarization with Distributed Microphones"],"prefix":"10.1109","author":[{"given":"Shota","family":"Horiguchi","sequence":"first","affiliation":[{"name":"Hitachi, Ltd.,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Takashima","sequence":"additional","affiliation":[{"name":"Hitachi, Ltd.,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paola","family":"Garcia","sequence":"additional","affiliation":[{"name":"CLSP & HLTCOE, Johns Hopkins University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yohei","family":"Kawaguchi","sequence":"additional","affiliation":[{"name":"Hitachi, Ltd.,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Corpus of spontaneous Japanese: Its design and evaluation","author":"maekawa","year":"2003","journal-title":"ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition"},{"key":"ref32","article-title":"MUSAN: A music, speech, and noise corpus","author":"snyder","year":"2015"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09905-3"},{"key":"ref34","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLRE"},{"key":"ref10","first-page":"5694","article-title":"Meeting recognition with asynchronous distributed microphone array using block-wise refinement of mask-based MVDR beam-former","author":"araki","year":"2018","journal-title":"ICASSP"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3088"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1050"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2008.4538680"},{"key":"ref14","first-page":"447","article-title":"Probabilistic speaker diarization with bag-of-words representations of speaker angle information","volume":"20","author":"ishiguro","year":"2011","journal-title":"IEEE TASLP"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1089"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616142"},{"key":"ref17","first-page":"2011","article-title":"Acoustic beam-forming for speaker diarization of meetings","volume":"15","author":"anguera","year":"2007","journal-title":"IEEE TASLP"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004031"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383490"},{"key":"ref28","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"NIPS 2016 Deep Learning Symposium"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053610"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref6","article-title":"Encoder-decoder based attractor calculation for end-to-end neural diarization","author":"horiguchi","year":"2021"},{"key":"ref29","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1602"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2961071"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101254"},{"key":"ref2","article-title":"A review of speaker diarization: Recent advances with deep learning","author":"park","year":"2021"},{"key":"ref9","first-page":"32","article-title":"Meeting recognition with asynchronous distributed microphone array","author":"araki","year":"2017","journal-title":"ASRU"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125954"},{"key":"ref20","first-page":"381","article-title":"Tack-ling real noisy reverberant meetings with all-neural source separation, counting, and diarization system","author":"kinoshita","year":"2020","journal-title":"ICASSP"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682650"},{"key":"ref21","first-page":"2632","article-title":"Multi-channel end-to-end speech recognition","author":"ochiai","year":"2017","journal-title":"ICML"},{"key":"ref24","first-page":"260","article-title":"FaS-Net: Low-latency adaptive beamforming for multi-microphone audio processing","author":"luo","year":"2019","journal-title":"ASRU"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-655"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414758"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054177"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746749.pdf?arnumber=9746749","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:07:48Z","timestamp":1660594068000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746749\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746749","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}