{"id":"https://openalex.org/W3161587262","doi":"https://doi.org/10.1109/icassp39728.2021.9413544","title":"A Real-Time Speaker Diarization System Based on Spatial Spectrum","display_name":"A Real-Time Speaker Diarization System Based on Spatial Spectrum","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161587262","doi":"https://doi.org/10.1109/icassp39728.2021.9413544","mag":"3161587262"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413544","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2107.09321","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101700479","display_name":"Siqi Zheng","orcid":"https://orcid.org/0000-0002-5481-7900"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siqi Zheng","raw_affiliation_strings":["Alibaba Group,Speech Lab","Speech Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"Speech Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021005147","display_name":"Weilong Huang","orcid":"https://orcid.org/0009-0000-5685-736X"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weilong Huang","raw_affiliation_strings":["Alibaba Group,Speech Lab","Speech Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"Speech Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002972091","display_name":"Xianliang Wang","orcid":"https://orcid.org/0000-0003-3462-608X"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xianliang Wang","raw_affiliation_strings":["Alibaba Group,Speech Lab","Speech Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"Speech Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109630497","display_name":"Hongbin Suo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongbin Suo","raw_affiliation_strings":["Alibaba Group,Speech Lab","Speech Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"Speech Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101628650","display_name":"Jinwei Feng","orcid":"https://orcid.org/0009-0000-2516-3891"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinwei Feng","raw_affiliation_strings":["Alibaba Group,Speech Lab","Speech Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"Speech Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061850214","display_name":"Zhijie Yan","orcid":"https://orcid.org/0000-0001-8065-0748"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhijie Yan","raw_affiliation_strings":["Alibaba Group,Speech Lab","Speech Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"Speech Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6251,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.903729,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7208","last_page":"7212"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9998999834060669,"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":0.9995999932289124,"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":0.925711989402771},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7921373844146729},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7600149512290955},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6176457405090332},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6139119267463684},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5771970152854919},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.42716988921165466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31811970472335815},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1272742748260498},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.07314109802246094},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06896501779556274}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.925711989402771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7921373844146729},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7600149512290955},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6176457405090332},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6139119267463684},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5771970152854919},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.42716988921165466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31811970472335815},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1272742748260498},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.07314109802246094},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06896501779556274},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413544","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2107.09321","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.09321","pdf_url":"https://arxiv.org/pdf/2107.09321","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:2107.09321","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.09321","pdf_url":"https://arxiv.org/pdf/2107.09321","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/4","score":0.4699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W126779258","https://openalex.org/W1515932869","https://openalex.org/W1524333225","https://openalex.org/W1606894530","https://openalex.org/W1997817740","https://openalex.org/W2060108923","https://openalex.org/W2148613904","https://openalex.org/W2403536560","https://openalex.org/W2499102192","https://openalex.org/W2638067502","https://openalex.org/W2726515241","https://openalex.org/W2767831780","https://openalex.org/W2805869973","https://openalex.org/W2896538040","https://openalex.org/W2963301902","https://openalex.org/W2963470929","https://openalex.org/W2989790778","https://openalex.org/W3015544392","https://openalex.org/W3015678936","https://openalex.org/W3095300891","https://openalex.org/W3097659012","https://openalex.org/W6631362777","https://openalex.org/W6713378954","https://openalex.org/W6740167877"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1977167953","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"describe":[4],"a":[5,19,25,93],"speaker":[6,35,70,88,124,129],"diarization":[7,36],"system":[8,147],"that":[9,138,145],"enables":[10],"localization":[11],"and":[12,41,152],"identification":[13,71],"of":[14,53,123],"all":[15],"speakers":[16,54,80],"present":[17],"in":[18,34,107],"conversation":[20,62],"or":[21,59],"meeting.":[22],"We":[23],"propose":[24],"novel":[26],"systematic":[27],"approach":[28,98,117],"to":[29,39,49,67,77,86,101,120,134],"tackle":[30],"several":[31],"long-standing":[32],"challenges":[33],"tasks:":[37],"(1)":[38],"segment":[40],"separate":[42],"overlapping":[43],"speech":[44],"from":[45],"two":[46],"speakers;":[47],"(2)":[48],"estimate":[50],"the":[51,61,83,103,136],"number":[52,130],"when":[55],"participants":[56],"may":[57],"enter":[58],"leave":[60],"at":[63],"any":[64],"time;":[65],"(3)":[66],"provide":[68],"accurate":[69],"on":[72],"short":[73],"text-independent":[74],"utterances;":[75],"(4)":[76],"track":[78,122],"down":[79],"movement":[81],"during":[82],"conversation;":[84],"(5)":[85],"detect":[87],"change":[89],"incidence":[90],"real-time.":[91],"First,":[92],"differential":[94],"directional":[95],"microphone":[96],"array-based":[97],"is":[99,118,132],"exploited":[100],"capture":[102],"target":[104],"speakers\u2019":[105],"voice":[106],"far-field":[108],"adverse":[109],"environment.":[110],"Second,":[111],"an":[112,127],"online":[113],"speaker-location":[114],"joint":[115],"clustering":[116],"proposed":[119],"keep":[121],"location.":[125],"Third,":[126],"instant":[128],"detector":[131],"developed":[133],"trigger":[135],"mechanism":[137],"separates":[139],"overlapped":[140],"speech.":[141],"The":[142],"results":[143],"suggest":[144],"our":[146],"effectively":[148],"incorporates":[149],"spatial":[150],"information":[151],"achieves":[153],"significant":[154],"gains.":[155]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
