{"id":"https://openalex.org/W4392903086","doi":"https://doi.org/10.1109/icassp48485.2024.10446168","title":"A Spatial Long-Term Iterative Mask Estimation Approach for Multi-Channel Speaker Diarization and Speech Recognition","display_name":"A Spatial Long-Term Iterative Mask Estimation Approach for Multi-Channel Speaker Diarization and Speech Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903086","doi":"https://doi.org/10.1109/icassp48485.2024.10446168"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5074945035","display_name":"Feng Ma","orcid":"https://orcid.org/0000-0002-1357-3006"},"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":"Feng Ma","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/A5103829995","display_name":"Yanhui Tu","orcid":"https://orcid.org/0000-0002-2923-958X"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanhui Tu","raw_affiliation_strings":["iFlytek Research,China","iFlytek Research, China"],"affiliations":[{"raw_affiliation_string":"iFlytek Research,China","institution_ids":["https://openalex.org/I173632517"]},{"raw_affiliation_string":"iFlytek Research, China","institution_ids":[]}]},{"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":"Maokui 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/A5033777521","display_name":"Ruoyu Wang","orcid":"https://orcid.org/0000-0002-3644-1284"},"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":"Ruoyu Wang","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/A5101926390","display_name":"Lei Sun","orcid":"https://orcid.org/0000-0001-7680-6455"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Sun","raw_affiliation_strings":["iFlytek Research,China","iFlytek Research, China"],"affiliations":[{"raw_affiliation_string":"iFlytek Research,China","institution_ids":["https://openalex.org/I173632517"]},{"raw_affiliation_string":"iFlytek Research, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065761465","display_name":"Zhongfu Ye","orcid":"https://orcid.org/0000-0002-3207-2258"},"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":"Zhongfu Ye","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/A5076812698","display_name":"Jia Pan","orcid":"https://orcid.org/0000-0001-9003-2054"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Pan","raw_affiliation_strings":["iFlytek Research,China","iFlytek Research, China"],"affiliations":[{"raw_affiliation_string":"iFlytek Research,China","institution_ids":["https://openalex.org/I173632517"]},{"raw_affiliation_string":"iFlytek Research, 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":10,"corresponding_author_ids":["https://openalex.org/A5074945035"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.0811,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73743194,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"12331","last_page":"12335"},"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":0.9951000213623047,"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":0.8880845308303833},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7675418853759766},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6873763203620911},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6379852294921875},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.49208420515060425},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.48865821957588196},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4444291293621063},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.43790096044540405},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4299105703830719},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4127742648124695},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38069307804107666},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07738736271858215}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8880845308303833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7675418853759766},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6873763203620911},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6379852294921875},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.49208420515060425},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.48865821957588196},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4444291293621063},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.43790096044540405},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4299105703830719},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4127742648124695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38069307804107666},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07738736271858215},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1713836045","display_name":null,"funder_award_id":"62171427","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1973787919","https://openalex.org/W2024490156","https://openalex.org/W2027227339","https://openalex.org/W2050875687","https://openalex.org/W2060108923","https://openalex.org/W2069884666","https://openalex.org/W2070707809","https://openalex.org/W2072548008","https://openalex.org/W2091432990","https://openalex.org/W2093225945","https://openalex.org/W2099741732","https://openalex.org/W2101045344","https://openalex.org/W2121767183","https://openalex.org/W2129934596","https://openalex.org/W2132605602","https://openalex.org/W2134642725","https://openalex.org/W2152131029","https://openalex.org/W2164764235","https://openalex.org/W2289394825","https://openalex.org/W2400339399","https://openalex.org/W2563666542","https://openalex.org/W2884797218","https://openalex.org/W2902894493","https://openalex.org/W2972492143","https://openalex.org/W3097263872","https://openalex.org/W4362683557","https://openalex.org/W4389315128","https://openalex.org/W6856665624"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1197719229","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2381158726","https://openalex.org/W2552734076","https://openalex.org/W2162158162","https://openalex.org/W1992796048","https://openalex.org/W1999004162"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"(DL)-based":[2],"speaker":[3,64,95,101,109,114,127,135],"diarization":[4,18,65,81,123,146,169],"methods":[5,14],"have":[6],"proven":[7],"powerful":[8],"performance":[9,62,173,189],"comparing":[10],"to":[11,35,39,59,88,113,117],"traditional":[12],"clustering-based":[13],"for":[15,144],"multi-talker":[16],"speech":[17],"and":[19,43,130,170],"recognition":[20,171],"in":[21,66,103,149,181,190],"farfield":[22],"scenes.":[23],"However,":[24],"most":[25],"DL-based":[26],"approaches":[27],"cannot":[28],"utilize":[29],"the":[30,36,61,72,90,108,118,122,133,141,145,156,182,187,191],"spatial":[31,50],"information":[32,124],"well":[33],"due":[34],"poor":[37],"robustness":[38],"unknown":[40],"array":[41],"topology":[42],"acoustic":[44,69],"scenario.":[45],"In":[46],"this":[47],"paper,":[48],"a":[49,104,178],"long-term":[51,105],"iterative":[52],"mask":[53],"estimation":[54],"(SLT-IME)":[55],"method":[56,166],"is":[57,86,128],"proposed":[58,165],"improve":[60,168],"of":[63,93,125,194],"various":[67],"real-world":[68],"scenarios.":[70],"First,":[71],"complex":[73],"angular":[74],"central":[75],"gaussian":[76],"mixture":[77],"model":[78],"(cACGMM)":[79],"with":[80],"results":[82,154],"as":[83,140],"initial":[84,142],"values":[85],"used":[87],"estimate":[89],"presence":[91],"probability":[92],"each":[94,97],"at":[96],"time-frequency":[98],"bin,":[99],"namely":[100],"masks,":[102],"chunk.":[106],"Then,":[107],"masks":[110],"are":[111],"converted":[112],"activities":[115],"according":[116],"threshold,":[119],"which":[120,126],"deliver":[121],"active":[129],"when.":[131],"Finally,":[132],"estimated":[134],"activity":[136],"can":[137,167],"also":[138,176],"serve":[139],"input":[143],"system,":[147],"resulting":[148],"improved":[150],"ASR":[151],"performance.":[152],"Experimental":[153],"on":[155],"CHiME-7":[157,195],"three":[158],"datasets":[159],"(CHiME-6,":[160],"DiPCo,":[161],"Mixer":[162],"6)":[163],"show":[164],"systems":[172],"simultaneously.":[174],"It":[175],"plays":[177],"key":[179],"role":[180],"ensemble":[183],"system":[184],"that":[185],"achieves":[186],"best":[188],"main":[192],"track":[193],"DASR":[196],"Challenge.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}