{"id":"https://openalex.org/W2889503488","doi":"https://doi.org/10.21437/interspeech.2018-2284","title":"Recognizing Overlapped Speech in Meetings: A Multichannel Separation Approach Using Neural Networks","display_name":"Recognizing Overlapped Speech in Meetings: A Multichannel Separation Approach Using Neural Networks","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889503488","doi":"https://doi.org/10.21437/interspeech.2018-2284","mag":"2889503488"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-2284","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1810.03655","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["Microsoft AI and Research, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065994318","display_name":"Hakan Erdo\u011fan","orcid":"https://orcid.org/0000-0003-3140-8642"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hakan Erdogan","raw_affiliation_strings":["Microsoft AI and Research, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345092","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0002-9011-7928"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Microsoft AI and Research, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101602536","display_name":"Xiong Xiao","orcid":"https://orcid.org/0009-0001-5128-6518"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiong Xiao","raw_affiliation_strings":["Microsoft AI and Research, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109977451","display_name":"Fil Alleva","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fil Alleva","raw_affiliation_strings":["Microsoft AI and Research, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.6414,"has_fulltext":false,"cited_by_count":101,"citation_normalized_percentile":{"value":0.98826827,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3038","last_page":"3042"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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":0.7764725089073181},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.7237920761108398},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6789799928665161},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6712750792503357},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5989340543746948},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4985959529876709},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.49114248156547546},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4862338602542877},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.44766849279403687},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.43943583965301514},{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.4282497465610504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35226011276245117},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18989166617393494},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12382274866104126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764725089073181},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7237920761108398},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6789799928665161},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6712750792503357},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5989340543746948},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4985959529876709},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.49114248156547546},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4862338602542877},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.44766849279403687},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.43943583965301514},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.4282497465610504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35226011276245117},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18989166617393494},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12382274866104126},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-2284","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1810.03655","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.03655","pdf_url":"https://arxiv.org/pdf/1810.03655","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1810.03655","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.03655","pdf_url":"https://arxiv.org/pdf/1810.03655","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W262275730","https://openalex.org/W1524333225","https://openalex.org/W1983812858","https://openalex.org/W2005733316","https://openalex.org/W2117678320","https://openalex.org/W2119203697","https://openalex.org/W2148613904","https://openalex.org/W2168729028","https://openalex.org/W2193413348","https://openalex.org/W2221409856","https://openalex.org/W2288502450","https://openalex.org/W2288645994","https://openalex.org/W2289480995","https://openalex.org/W2407022425","https://openalex.org/W2517616541","https://openalex.org/W2533523411","https://openalex.org/W2622203030","https://openalex.org/W2640112133","https://openalex.org/W2734774145","https://openalex.org/W2743392628","https://openalex.org/W2747357425","https://openalex.org/W2750380122","https://openalex.org/W2757672955","https://openalex.org/W2766589983","https://openalex.org/W2769180089","https://openalex.org/W2787692317","https://openalex.org/W2803322398","https://openalex.org/W2803583024","https://openalex.org/W2949640717","https://openalex.org/W2963590452","https://openalex.org/W3099832538"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W2333799855","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2351687372","https://openalex.org/W2004087835","https://openalex.org/W2314871050"],"abstract_inverted_index":{"The":[0,83],"goal":[1],"of":[2,19,92,103,129,180],"this":[3,183],"work":[4],"is":[5,123,184],"to":[6,60,141,193],"develop":[7],"a":[8,31,38,42,66,80,87,142,159,163],"meeting":[9,104,122,151,196],"transcription":[10,152],"system":[11,153,160],"that":[12,188],"can":[13,137],"recognize":[14],"speech":[15,25,52,143,191],"even":[16],"when":[17],"utterances":[18],"different":[20,99],"speakers":[21],"are":[22,172],"overlapped.":[23],"While":[24],"overlaps":[26],"have":[27,55],"been":[28,46],"regarded":[29],"as":[30],"major":[32],"obstacle":[33],"in":[34,120,174],"accurately":[35],"transcribing":[36],"meetings,":[37],"traditional":[39],"beamformer":[40,167],"with":[41],"single":[43],"output":[44,93,131,135],"has":[45,86],"exclusively":[47],"used":[48],"because":[49],"previously":[50],"proposed":[51],"separation":[53],"techniques":[54],"critical":[56],"constraints":[57],"for":[58,146],"application":[59],"real":[61,195],"meetings.":[62],"This":[63],"paper":[64],"proposes":[65],"new":[67],"signal":[68,112,136],"processing":[69],"module,":[70],"called":[71],"an":[72,108],"unmixing":[73,84,156],"transducer,":[74],"and":[75,106,125,148],"describes":[76],"its":[77],"implementation":[78],"using":[79,154],"windowed":[81],"BLSTM.":[82],"transducer":[85,157],"fixed":[88],"number,":[89],"say":[90],"J,":[91],"channels,":[94],"where":[95],"J":[96,114],"may":[97],"be":[98,138],"from":[100,127],"the":[101,121,130,155,178,185],"number":[102],"attendees,":[105],"transforms":[107],"input":[109],"multi-channel":[110],"acoustic":[111],"into":[113],"time-synchronous":[115],"audio":[116],"streams.":[117],"Each":[118],"utterance":[119],"separated":[124],"emitted":[126],"one":[128],"channels.":[132],"Then,":[133],"each":[134],"simply":[139],"fed":[140],"recognition":[144,192],"back-end":[145],"segmentation":[147],"transcription.":[149],"Our":[150],"outperforms":[158],"based":[161],"on":[162],"state-of-the-art":[164],"neural":[165],"mask-based":[166],"by":[168],"10.8%.":[169],"Significant":[170],"improvements":[171],"observed":[173],"overlapped":[175,190],"segments.":[176],"To":[177],"best":[179],"our":[181],"knowledge,":[182],"first":[186],"report":[187],"applies":[189],"unconstrained":[194],"audio.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}