{"id":"https://openalex.org/W4321780117","doi":"https://doi.org/10.1109/taslp.2023.3244513","title":"QDM-SSD: Quality-Aware Dynamic Masking for Separation-Based Speaker Diarization","display_name":"QDM-SSD: Quality-Aware Dynamic Masking for Separation-Based Speaker Diarization","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4321780117","doi":"https://doi.org/10.1109/taslp.2023.3244513"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3244513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3244513","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/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":true,"raw_author_name":"Shu-Tong Niu","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, 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":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, 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/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":"Lei Sun","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112134613","display_name":"Yu Hu","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":"Yu Hu","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"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":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5064699619"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.6993,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73930252,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"31","issue":null,"first_page":"1037","last_page":"1049"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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":0.7973589897155762},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6775033473968506},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.66986083984375},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5047544240951538},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.48216837644577026},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.36436864733695984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7973589897155762},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6775033473968506},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.66986083984375},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5047544240951538},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.48216837644577026},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.36436864733695984},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3244513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3244513","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"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"}],"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":70,"referenced_works":["https://openalex.org/W262275730","https://openalex.org/W1485783873","https://openalex.org/W1494198834","https://openalex.org/W1607302042","https://openalex.org/W2038101708","https://openalex.org/W2046056978","https://openalex.org/W2081074144","https://openalex.org/W2093499222","https://openalex.org/W2098726438","https://openalex.org/W2144125830","https://openalex.org/W2150769028","https://openalex.org/W2345067732","https://openalex.org/W2460742184","https://openalex.org/W2587994092","https://openalex.org/W2734774145","https://openalex.org/W2746574320","https://openalex.org/W2800664709","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2915347754","https://openalex.org/W2939246703","https://openalex.org/W2952218014","https://openalex.org/W2952752702","https://openalex.org/W2962866211","https://openalex.org/W2962905190","https://openalex.org/W2963470929","https://openalex.org/W2989790778","https://openalex.org/W2996787432","https://openalex.org/W3010196324","https://openalex.org/W3015544392","https://openalex.org/W3015780472","https://openalex.org/W3015810999","https://openalex.org/W3016232124","https://openalex.org/W3016244460","https://openalex.org/W3020336359","https://openalex.org/W3024085360","https://openalex.org/W3025260599","https://openalex.org/W3095212884","https://openalex.org/W3095253761","https://openalex.org/W3095717210","https://openalex.org/W3096893582","https://openalex.org/W3099330747","https://openalex.org/W3111481301","https://openalex.org/W3147778289","https://openalex.org/W3160936850","https://openalex.org/W3162347631","https://openalex.org/W3163652268","https://openalex.org/W3174940004","https://openalex.org/W3182885906","https://openalex.org/W3195050710","https://openalex.org/W3196595845","https://openalex.org/W3196781856","https://openalex.org/W3197179619","https://openalex.org/W3197980326","https://openalex.org/W3204618061","https://openalex.org/W3207834622","https://openalex.org/W3208240190","https://openalex.org/W3212886388","https://openalex.org/W4224933752","https://openalex.org/W4225890157","https://openalex.org/W4297841674","https://openalex.org/W4385245566","https://openalex.org/W4406592015","https://openalex.org/W6631190155","https://openalex.org/W6713631176","https://openalex.org/W6774558098","https://openalex.org/W6787439801","https://openalex.org/W6798708994","https://openalex.org/W6802591457","https://openalex.org/W6931392099"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"We":[0,12],"improve":[1,140],"iterative":[2],"separation-based":[3],"speaker":[4,39,57],"diarization":[5,100],"(ISSD)":[6],"with":[7,19,108],"quality-aware":[8],"dynamic":[9],"masking":[10],"(QDM).":[11],"call":[13],"the":[14,23,34,50,70,84,93,99,141],"proposed":[15,94],"framework":[16,96],"QDM-SSD.":[17],"Compared":[18],"ISSD,":[20],"QDM-SSD":[21,47,95,111,133],"enhances":[22],"simulated":[24],"data":[25,44,52,62,122],"used":[26],"for":[27],"model":[28],"adaptation":[29,51,71],"through":[30],"QDM":[31],"to":[32,43,61,114,116,127,139],"alleviate":[33],"influence":[35],"of":[36,143],"errors":[37],"in":[38,75],"priors.":[40],"In":[41],"addition":[42],"quality":[45],"purification,":[46],"also":[48],"makes":[49],"sparse":[53],"by":[54,104],"automatically":[55],"adjusting":[56],"overlap":[58],"ratios":[59],"according":[60],"quality.":[63],"Furthermore,":[64],"using":[65],"a":[66,137],"sliding":[67],"window":[68],"over":[69],"data,":[72],"clean":[73],"regions":[74],"speech":[76,88,121,146],"segments":[77],"can":[78,97,134],"be":[79],"better":[80],"localized.":[81],"Experiments":[82],"on":[83],"two-speaker":[85,118],"conversational":[86],"telephone":[87,120],"(CTS)":[89],"corpus":[90],"show":[91],"that":[92,132],"reduce":[98],"error":[101],"rate":[102],"(DER)":[103],"18.56%":[105],"relatively":[106],"compared":[107],"ISSD.":[109],"Moreover,":[110],"is":[112],"shown":[113],"generalize":[115],"other":[117],"non-conversation":[119],"sets":[123],"where":[124],"ISSD":[125],"fails":[126],"work.":[128],"Finally,":[129],"we":[130],"demonstrate":[131],"serve":[135],"as":[136],"front-end":[138],"performances":[142],"back-end":[144],"automatic":[145],"recognition.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}