{"id":"https://openalex.org/W2917174945","doi":"https://doi.org/10.1109/icassp.2019.8682572","title":"All-neural Online Source Separation, Counting, and Diarization for Meeting Analysis","display_name":"All-neural Online Source Separation, Counting, and Diarization for Meeting Analysis","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2917174945","doi":"https://doi.org/10.1109/icassp.2019.8682572","mag":"2917174945"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682572","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1902.07881","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015424386","display_name":"Thilo von Neumann","orcid":"https://orcid.org/0000-0002-7717-8670"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]},{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["DE","JP"],"is_corresponding":false,"raw_author_name":"Thilo von Neumann","raw_affiliation_strings":["Department of Communications Engineering, Paderborn University, Paderborn, Germany","NTT Communication Science Labs. NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Communications Engineering, Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]},{"raw_affiliation_string":"NTT Communication Science Labs. NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Communication Science Labs. NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Labs. NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Communication Science Labs. NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Labs. NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoko Araki","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Communication Science Labs. NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Labs. NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Communication Science Labs. NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Labs. NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082075598","display_name":"Reinhold Haeb\u2010Umbach","orcid":"https://orcid.org/0000-0001-9468-7330"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Reinhold Haeb-Umbach","raw_affiliation_strings":["Department of Communications Engineering, Paderborn University, Paderborn, Germany","[Department of Communications Engineering, Paderborn University, Paderborn, Germany]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Communications Engineering, Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]},{"raw_affiliation_string":"[Department of Communications Engineering, Paderborn University, Paderborn, Germany]","institution_ids":["https://openalex.org/I206945453"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"91","last_page":"95"},"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":0.9997000098228455,"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":0.9980000257492065,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.8630577325820923},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7302744388580322},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6471292972564697},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5923488140106201},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5868824124336243},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5757559537887573},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5006711483001709},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4438720941543579},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.43675294518470764},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4093160331249237},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22934451699256897},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09867334365844727},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07380649447441101}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8630577325820923},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7302744388580322},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6471292972564697},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5923488140106201},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5868824124336243},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5757559537887573},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5006711483001709},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4438720941543579},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.43675294518470764},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4093160331249237},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22934451699256897},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09867334365844727},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07380649447441101},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2019.8682572","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1902.07881","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.07881","pdf_url":"https://arxiv.org/pdf/1902.07881","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"},{"id":"doi:10.48550/arxiv.1902.07881","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1902.07881","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2917174945","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1902.07881","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.07881","pdf_url":"https://arxiv.org/pdf/1902.07881","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":[{"id":"https://metadata.un.org/sdg/16","score":0.5899999737739563,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2917174945.pdf","grobid_xml":"https://content.openalex.org/works/W2917174945.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2081074144","https://openalex.org/W2101169486","https://openalex.org/W2125336414","https://openalex.org/W2150769028","https://openalex.org/W2159284737","https://openalex.org/W2221409856","https://openalex.org/W2325237720","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2587150483","https://openalex.org/W2612434969","https://openalex.org/W2734774145","https://openalex.org/W2739041555","https://openalex.org/W2799930831","https://openalex.org/W2889381673","https://openalex.org/W2889418727","https://openalex.org/W2889503488","https://openalex.org/W2889755093","https://openalex.org/W2891054259","https://openalex.org/W2891833136","https://openalex.org/W2939771864","https://openalex.org/W6701498492","https://openalex.org/W6737575990"],"related_works":["https://openalex.org/W2952752702","https://openalex.org/W2972346374","https://openalex.org/W3016244460","https://openalex.org/W2103348173","https://openalex.org/W3010196324","https://openalex.org/W2140192608","https://openalex.org/W3160044950","https://openalex.org/W277919747","https://openalex.org/W3008357631","https://openalex.org/W2973981642","https://openalex.org/W2534034218","https://openalex.org/W3085288553","https://openalex.org/W2782767377","https://openalex.org/W3157070662","https://openalex.org/W3120137480","https://openalex.org/W3210727692","https://openalex.org/W3164674954","https://openalex.org/W3164949054","https://openalex.org/W2971668813","https://openalex.org/W2401489983"],"abstract_inverted_index":{"Automatic":[0],"meeting":[1],"analysis":[2],"comprises":[3],"the":[4,12,54,97,111,122,130],"tasks":[5],"of":[6,14,87,113,121,149],"speaker":[7,9,62],"counting,":[8,63],"diarization,":[10],"and":[11,65,76,136],"separation":[13,124],"overlapped":[15],"speech,":[16],"followed":[17],"by":[18],"automatic":[19],"speech":[20],"recognition.":[21],"This":[22],"all":[23],"has":[24,44],"to":[25,60,144],"be":[26],"carried":[27],"out":[28],"on":[29,47],"arbitrarily":[30],"long":[31],"sessions":[32],"and,":[33],"ideally,":[34],"in":[35,72],"an":[36,57,145],"online":[37],"or":[38],"block-online":[39,74],"manner.":[40],"While":[41],"significant":[42],"progress":[43],"been":[45],"made":[46],"individual":[48],"tasks,":[49],"this":[50],"paper":[51],"presents":[52],"for":[53,84,96],"first":[55],"time":[56,88,106,132],"all-neural":[58],"approach":[59],"simultaneous":[61],"diarization":[64,135],"source":[66,137],"separation.":[67],"The":[68,100,115],"NN-based":[69],"estimator":[70],"operates":[71],"a":[73,85,92],"fashion":[75],"tracks":[77],"speakers":[78],"even":[79,141],"if":[80],"they":[81],"remain":[82],"silent":[83],"number":[86,112,148],"blocks,":[89],"thus":[90],"learning":[91],"stable":[93],"output":[94],"order":[95],"separated":[98],"sources.":[99,114],"neural":[101],"network":[102],"is":[103,126],"recurrent":[104],"over":[105,110],"as":[107,109],"well":[108,143],"simulation":[116],"experiments":[117],"show":[118],"that":[119],"state":[120],"art":[123],"performance":[125],"achieved,":[127],"while":[128],"at":[129],"same":[131],"delivering":[133],"good":[134],"counting":[138],"results.":[139],"It":[140],"generalizes":[142],"unseen":[146],"large":[147],"blocks.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}