{"id":"https://openalex.org/W4391021771","doi":"https://doi.org/10.1109/asru57964.2023.10389615","title":"Semi-Supervised Multi-Channel Speaker Diarization With Cross-Channel Attention","display_name":"Semi-Supervised Multi-Channel Speaker Diarization With Cross-Channel Attention","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021771","doi":"https://doi.org/10.1109/asru57964.2023.10389615"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389615","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5100861162","display_name":"Shilong Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shilong Wu","raw_affiliation_strings":["University of Science and Technology of China,China","University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China,China","University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018657729","display_name":"Maokui He","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mao-Kui He","raw_affiliation_strings":["University of Science and Technology of China,China","University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064699619","display_name":"Shutong Niu","orcid":"https://orcid.org/0000-0003-0315-1042"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shutong Niu","raw_affiliation_strings":["University of Science and Technology of China,China","University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442516","display_name":"Hang Chen","orcid":"https://orcid.org/0000-0001-9999-1358"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Chen","raw_affiliation_strings":["University of Science and Technology of China,China","University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044202868","display_name":"Haitao Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haitao Tang","raw_affiliation_strings":["iFlytek,China","iFlytek, China"],"affiliations":[{"raw_affiliation_string":"iFlytek,China","institution_ids":[]},{"raw_affiliation_string":"iFlytek, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["Georgia Institute of Technology,USA","Georgia Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100861162"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19167075,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9990000128746033,"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":0.9850000143051147,"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":0.7400709390640259},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.7259023785591125},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6282325983047485},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5997990369796753},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3129914402961731},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1575663983821869}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7400709390640259},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.7259023785591125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6282325983047485},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5997990369796753},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3129914402961731},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1575663983821869}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389615","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.75}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1607302042","https://openalex.org/W1890834058","https://openalex.org/W2081074144","https://openalex.org/W2093499222","https://openalex.org/W2150769028","https://openalex.org/W2184906052","https://openalex.org/W2402146185","https://openalex.org/W2508048623","https://openalex.org/W2746574320","https://openalex.org/W2890964092","https://openalex.org/W2891247151","https://openalex.org/W2915347754","https://openalex.org/W2952218014","https://openalex.org/W2963470929","https://openalex.org/W2972949456","https://openalex.org/W3008357631","https://openalex.org/W3010830830","https://openalex.org/W3015522062","https://openalex.org/W3020336359","https://openalex.org/W3024869864","https://openalex.org/W3025260599","https://openalex.org/W3099330747","https://openalex.org/W3140898556","https://openalex.org/W3145204487","https://openalex.org/W3160207687","https://openalex.org/W3169722760","https://openalex.org/W3178462146","https://openalex.org/W3195050710","https://openalex.org/W3196781856","https://openalex.org/W3206479921","https://openalex.org/W3207834622","https://openalex.org/W3212886388","https://openalex.org/W4221165517","https://openalex.org/W4224917363","https://openalex.org/W4289824098","https://openalex.org/W4319862214","https://openalex.org/W4362683557","https://openalex.org/W4385823318","https://openalex.org/W4389315128"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"Most":[0],"neural":[1],"speaker":[2,25,61],"diarization":[3,26],"systems":[4],"rely":[5],"on":[6,66,95,103],"sufficient":[7],"manual":[8],"training":[9,32,79,115,124],"data":[10,33,137],"labels,":[11],"which":[12,71],"are":[13],"hard":[14],"to":[15,28,55,91,108,130],"collect":[16],"under":[17],"real-world":[18],"scenarios.":[19],"This":[20],"paper":[21],"proposes":[22],"a":[23],"semi-supervised":[24],"system":[27,84,127],"utilize":[29],"large-scale":[30],"multi-channel":[31],"by":[34],"generating":[35],"pseudo-labels":[36],"for":[37,138],"unlabeled":[38],"data.":[39],"Furthermore,":[40],"we":[41],"introduce":[42],"cross-channel":[43],"attention":[44],"into":[45],"the":[46,67,78,92,96,104,110,131],"Neural":[47],"Speaker":[48],"Diarization":[49],"Using":[50],"Memory-Aware":[51],"Multi-Speaker":[52],"Embedding":[53],"(NSD-MA-MSE)":[54],"learn":[56],"channel":[57],"contextual":[58],"information":[59],"of":[60,77,112],"embeddings":[62],"better.":[63],"Experimental":[64],"results":[65,132],"CHiME-7":[68],"Mixer6":[69],"dataset":[70,107],"only":[72],"contains":[73],"partial":[74,114],"speakers\u2019":[75],"labels":[76],"set,":[80],"show":[81],"that":[82],"our":[83,126],"achieved":[85],"57.01%":[86],"relative":[87],"DER":[88],"reduction":[89],"compared":[90],"clustering-based":[93],"model":[94],"development":[97],"set.":[98],"We":[99],"further":[100],"conducted":[101],"experiments":[102],"CHiME-":[105],"6":[106],"simulate":[109],"scenario":[111],"missing":[113],"set":[116],"labels.":[117],"When":[118],"using":[119,134],"80%":[120],"and":[121],"50%":[122],"labeled":[123,136],"data,":[125],"performs":[128],"comparably":[129],"obtained":[133],"100%":[135],"training.":[139]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}