{"id":"https://openalex.org/W3207570488","doi":"https://doi.org/10.1109/icassp43922.2022.9746749","title":"Multi-Channel End-To-End Neural Diarization with Distributed Microphones","display_name":"Multi-Channel End-To-End Neural Diarization with Distributed Microphones","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3207570488","doi":"https://doi.org/10.1109/icassp43922.2022.9746749","mag":"3207570488"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746749","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026324656","display_name":"Shota Horiguchi","orcid":"https://orcid.org/0000-0002-3166-4956"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shota Horiguchi","raw_affiliation_strings":["Hitachi, Ltd.,Japan","Hitachi, Ltd., Japan"],"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd.,Japan","institution_ids":["https://openalex.org/I65143321"]},{"raw_affiliation_string":"Hitachi, Ltd., Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087545401","display_name":"Yuki Takashima","orcid":"https://orcid.org/0000-0001-8489-9487"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Takashima","raw_affiliation_strings":["Hitachi, Ltd.,Japan","Hitachi, Ltd., Japan"],"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd.,Japan","institution_ids":["https://openalex.org/I65143321"]},{"raw_affiliation_string":"Hitachi, Ltd., Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059858850","display_name":"Leibny Paola Garcia","orcid":"https://orcid.org/0000-0002-7449-5726"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paola Garcia","raw_affiliation_strings":["CLSP & HLTCOE, Johns Hopkins University,USA"],"affiliations":[{"raw_affiliation_string":"CLSP & HLTCOE, Johns Hopkins University,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052394367","display_name":"Yohei Kawaguchi","orcid":"https://orcid.org/0000-0002-2329-5441"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yohei Kawaguchi","raw_affiliation_strings":["Hitachi, Ltd.,Japan","Hitachi, Ltd., Japan"],"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd.,Japan","institution_ids":["https://openalex.org/I65143321"]},{"raw_affiliation_string":"Hitachi, Ltd., Japan","institution_ids":["https://openalex.org/I65143321"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5026324656"],"corresponding_institution_ids":["https://openalex.org/I65143321"],"apc_list":null,"apc_paid":null,"fwci":1.769,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.86419221,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7332","last_page":"7336"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7945277690887451},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.7612431049346924},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.6697804927825928},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6333553194999695},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6246835589408875},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6146901845932007},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.530756950378418},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45301488041877747},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4394722282886505},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.27089858055114746},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2688426375389099},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.17552843689918518},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11597153544425964},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08096969127655029}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7945277690887451},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.7612431049346924},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6697804927825928},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6333553194999695},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6246835589408875},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6146901845932007},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.530756950378418},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45301488041877747},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4394722282886505},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.27089858055114746},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2688426375389099},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.17552843689918518},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11597153544425964},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08096969127655029},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746749","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2039206676","https://openalex.org/W2081074144","https://openalex.org/W2141398670","https://openalex.org/W2148613904","https://openalex.org/W2219249508","https://openalex.org/W2600628583","https://openalex.org/W2696967604","https://openalex.org/W2785745830","https://openalex.org/W2889664202","https://openalex.org/W2898268964","https://openalex.org/W2900092534","https://openalex.org/W2954695182","https://openalex.org/W2963403868","https://openalex.org/W2964121744","https://openalex.org/W2964391865","https://openalex.org/W2972949456","https://openalex.org/W2997419692","https://openalex.org/W3004309045","https://openalex.org/W3008849579","https://openalex.org/W3015372568","https://openalex.org/W3015679215","https://openalex.org/W3016244460","https://openalex.org/W3025260599","https://openalex.org/W3034729383","https://openalex.org/W3094893851","https://openalex.org/W3095212884","https://openalex.org/W3097700828","https://openalex.org/W3104196160","https://openalex.org/W3105031100","https://openalex.org/W3125596972","https://openalex.org/W3126531707","https://openalex.org/W3133848124","https://openalex.org/W3140898556","https://openalex.org/W3169722760","https://openalex.org/W3174648740","https://openalex.org/W3178462146","https://openalex.org/W3181157543","https://openalex.org/W3212886388","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6660414670","https://openalex.org/W6681922338","https://openalex.org/W6688816777","https://openalex.org/W6735168207","https://openalex.org/W6739901393","https://openalex.org/W6747694984","https://openalex.org/W6754733423","https://openalex.org/W6768303171","https://openalex.org/W6774249064","https://openalex.org/W6779469704","https://openalex.org/W6780226713","https://openalex.org/W6790122275","https://openalex.org/W6797229353"],"related_works":["https://openalex.org/W2545798066","https://openalex.org/W2385145472","https://openalex.org/W2351541234","https://openalex.org/W1969439651","https://openalex.org/W2013108665","https://openalex.org/W2259411108","https://openalex.org/W2738771020","https://openalex.org/W1607021895","https://openalex.org/W2733029664","https://openalex.org/W2801062816"],"abstract_inverted_index":{"Recent":[0],"progress":[1],"on":[2],"end-to-end":[3],"neural":[4,15],"diarization":[5,11],"(EEND)":[6],"has":[7],"en-abled":[8],"overlap-aware":[9],"speaker":[10],"with":[12,36,101],"a":[13,43,69,92,102],"single":[14],"net-work.":[16],"This":[17],"paper":[18],"proposes":[19],"to":[20],"enhance":[21],"EEND":[22,35,90],"by":[23],"using":[24,73],"multi-channel":[25,44,93,121],"signals":[26],"from":[27,139],"distributed":[28,63],"microphones.":[29],"We":[30,66,105],"replace":[31],"Transformer":[32],"en-coders":[33],"in":[34,125,128],"two":[37],"types":[38],"of":[39,53,58,132],"encoders":[40],"that":[41,84,108],"process":[42],"input:":[45],"spatio-temporal":[46],"and":[47,56,60,79],"co-attention":[48],"encoders.":[49],"Both":[50],"are":[51,136],"independent":[52],"the":[54,85,109,130,140],"number":[55],"geometry":[57],"microphones":[59],"suitable":[61],"for":[62],"microphone":[64],"settings.":[65],"also":[67,106],"propose":[68],"model":[70],"adaptation":[71],"method":[72,87,111],"only":[74],"single-channel":[75,103],"recordings.":[76],"With":[77],"simulated":[78],"real-recorded":[80],"datasets,":[81],"we":[82],"demonstrated":[83],"proposed":[86,110],"outperformed":[88],"conventional":[89],"when":[91,115],"in-put":[94],"was":[95],"given":[96,120],"while":[97],"maintaining":[98],"comparable":[99],"performance":[100],"input.":[104],"showed":[107],"performed":[112],"well":[113],"even":[114],"spatial":[116],"information":[117],"is":[118],"inoperative":[119],"inputs,":[122],"such":[123],"as":[124],"hybrid":[126],"meetings":[127],"which":[129],"utterances":[131],"multiple":[133],"remote":[134],"participants":[135],"played":[137],"back":[138],"same":[141],"loudspeaker.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}