{"id":"https://openalex.org/W7138912792","doi":"https://doi.org/10.1609/aaai.v40i40.40745","title":"SpeakerLM: End-to-End Versatile Speaker Diarization and Recognition with Multimodal Large Language Models","display_name":"SpeakerLM: End-to-End Versatile Speaker Diarization and Recognition with Multimodal Large Language Models","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138912792","doi":"https://doi.org/10.1609/aaai.v40i40.40745"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i40.40745","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i40.40745","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40745/44706","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40745/44706","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101192752","display_name":"Han Yin","orcid":"https://orcid.org/0009-0000-1759-4579"},"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":"Han Yin","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019204904","display_name":"Ya\u2010Feng Chen","orcid":"https://orcid.org/0009-0004-4446-1391"},"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":"Yafeng Chen","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129782467","display_name":"Chong Deng","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":"Chong Deng","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102891716","display_name":"Luyao Cheng","orcid":"https://orcid.org/0009-0006-1311-8448"},"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":"Luyao Cheng","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129885548","display_name":"Hui Wang","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":"Hui Wang","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123944470","display_name":"Chao-Hong Tan","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":"Chao-Hong Tan","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qian Chen","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":"Qian Chen","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129937411","display_name":"Wen Wang","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":"Wen Wang","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124042270","display_name":"Xiangang Li","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":"Xiangang Li","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210095624"],"apc_list":null,"apc_paid":null,"fwci":21.2894,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.97962549,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"40","issue":"40","first_page":"34467","last_page":"34475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9186000227928162,"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":0.9186000227928162,"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":0.014299999922513962,"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":0.008700000122189522,"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":0.7878999710083008},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6460000276565552},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5785999894142151},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5723999738693237},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5307000279426575},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4846000075340271},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3806000053882599},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.3700000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8321999907493591},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7878999710083008},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6732000112533569},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6460000276565552},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5785999894142151},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5723999738693237},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5307000279426575},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4846000075340271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4681999981403351},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3806000053882599},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3483999967575073},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3422999978065491},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3255999982357025},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30219998955726624},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2599000036716461},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i40.40745","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i40.40745","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40745/44706","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i40.40745","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i40.40745","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40745/44706","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138912792.pdf","grobid_xml":"https://content.openalex.org/works/W7138912792.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,57],"Speaker":[1],"Diarization":[2],"and":[3,13,33,52,73,84,106,157,166,193],"Recognition":[4],"(SDR)":[5],"task":[6,23],"aims":[7],"to":[8,113],"predict":[9],"``who":[10],"spoke":[11],"when":[12],"what''":[14],"within":[15],"an":[16,109],"audio":[17],"clip,":[18],"which":[19],"is":[20,135],"a":[21,41,94,120,139],"crucial":[22],"in":[24,69,108],"various":[25],"real-world":[26,116],"multi-speaker":[27],"scenarios":[28],"such":[29,47,64],"as":[30,48,65],"meeting":[31],"transcription":[32],"dialogue":[34],"systems.":[35],"Existing":[36],"SDR":[37,101,128,169,184],"systems":[38,59],"typically":[39],"adopt":[40],"cascaded":[42,58,161],"framework,":[43],"combining":[44],"multiple":[45],"modules":[46],"speaker":[49,122,131,178,190],"diarization":[50],"(SD)":[51],"automatic":[53],"speech":[54],"recognition":[55],"(ASR).":[56],"suffer":[60],"from":[61],"several":[62],"limitations,":[63,90],"error":[66],"propagation,":[67],"difficulty":[68],"handling":[70],"overlapping":[71],"speech,":[72],"lack":[74],"of":[75,186,196],"joint":[76],"optimization":[77],"for":[78,100],"exploring":[79],"the":[80,176],"synergy":[81],"between":[82],"SD":[83,105],"ASR":[85,107],"tasks.":[86],"To":[87],"address":[88],"these":[89],"we":[91,118],"introduce":[92],"SpeakerLM,":[93,126],"unified":[95],"multimodal":[96],"large":[97],"language":[98],"model":[99],"that":[102,150,175],"jointly":[103],"performs":[104],"end-to-end":[110],"manner.":[111],"Moreover,":[112],"facilitate":[114],"diverse":[115,189],"scenarios,":[117],"incorporate":[119],"flexible":[121],"registration":[123,132,179,191],"mechanism":[124,180],"into":[125],"enabling":[127],"under":[129],"different":[130],"settings.":[133],"SpeakerLM":[134,151,187],"progressively":[136],"developed":[137],"with":[138],"multi-stage":[140],"training":[141],"strategy":[142],"on":[143,163],"large-scale":[144],"real":[145],"data.":[146],"Extensive":[147],"experiments":[148],"show":[149,174],"demonstrates":[152],"strong":[153],"data":[154],"scaling":[155],"capability":[156],"generalizability,":[158],"outperforming":[159],"state-of-the-art":[160],"baselines":[162],"both":[164],"in-domain":[165],"out-of-domain":[167],"public":[168],"benchmarks.":[170],"Furthermore,":[171],"experimental":[172],"results":[173],"proposed":[177],"effectively":[181],"ensures":[182],"robust":[183],"performance":[185],"across":[188],"conditions":[192],"varying":[194],"numbers":[195],"registered":[197],"speakers.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-20T00:00:00"}