{"id":"https://openalex.org/W4408352172","doi":"https://doi.org/10.1109/icassp49660.2025.10888389","title":"3D-Speaker-Toolkit: An Open-Source Toolkit for Multimodal Speaker Verification and Diarization","display_name":"3D-Speaker-Toolkit: An Open-Source Toolkit for Multimodal Speaker Verification and Diarization","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352172","doi":"https://doi.org/10.1109/icassp49660.2025.10888389"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5003578886","display_name":"Yafeng Chen","orcid":"https://orcid.org/0000-0002-5459-4428"},"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":["Alibaba Group,Speech Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014586639","display_name":"Siqi Zheng","orcid":"https://orcid.org/0000-0002-4467-8505"},"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460802","display_name":"Hui Wang","orcid":"https://orcid.org/0000-0002-5208-8329"},"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":["Alibaba Group,Speech Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","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":["Alibaba Group,Speech Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034739222","display_name":"Tinglong Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tinglong Zhu","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011787904","display_name":"Rongjie Huang","orcid":"https://orcid.org/0000-0002-1695-9000"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongjie Huang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100686893","display_name":"Chong Deng","orcid":"https://orcid.org/0000-0002-7287-7042"},"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":["Alibaba Group,Speech Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428454","display_name":"Qian Chen","orcid":"https://orcid.org/0000-0002-1487-5479"},"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":["Alibaba Group,Speech Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101777591","display_name":"Shiliang Zhang","orcid":"https://orcid.org/0000-0002-9524-1602"},"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":"Shiliang Zhang","raw_affiliation_strings":["Alibaba Group,Speech Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115592093","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0001-8392-3457"},"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":["Alibaba Group,Speech Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108913367","display_name":"Xihao Li","orcid":null},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xihao Li","raw_affiliation_strings":["University of North Carolina,Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Carolina,Chapel Hill","institution_ids":["https://openalex.org/I114027177"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9973000288009644,"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":0.9927999973297119,"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":0.8177146911621094},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7577630281448364},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5764402151107788},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.5725208520889282},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5118734240531921},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47825872898101807},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.169195294380188},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.09920242428779602}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8177146911621094},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7577630281448364},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5764402151107788},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5725208520889282},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5118734240531921},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47825872898101807},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.169195294380188},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.09920242428779602}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1875623881","https://openalex.org/W2122364000","https://openalex.org/W2132914434","https://openalex.org/W2194775991","https://openalex.org/W2890964092","https://openalex.org/W2915347754","https://openalex.org/W2928165649","https://openalex.org/W2962780374","https://openalex.org/W2962788625","https://openalex.org/W2963604034","https://openalex.org/W2972449503","https://openalex.org/W2972729214","https://openalex.org/W2981087920","https://openalex.org/W3013020904","https://openalex.org/W3015598461","https://openalex.org/W3020336359","https://openalex.org/W3024869864","https://openalex.org/W3035693354","https://openalex.org/W3038871978","https://openalex.org/W3094374485","https://openalex.org/W3095851463","https://openalex.org/W3100648197","https://openalex.org/W3142516134","https://openalex.org/W3159481202","https://openalex.org/W3163421828","https://openalex.org/W3167533889","https://openalex.org/W3178462146","https://openalex.org/W3196117288","https://openalex.org/W3204618061","https://openalex.org/W3206008172","https://openalex.org/W3212886388","https://openalex.org/W4200633018","https://openalex.org/W4206908380","https://openalex.org/W4221144444","https://openalex.org/W4224925136","https://openalex.org/W4286378963","https://openalex.org/W4290995108","https://openalex.org/W4297841834","https://openalex.org/W4319862473","https://openalex.org/W4367597591","https://openalex.org/W4372340947","https://openalex.org/W4372346385","https://openalex.org/W4382602944","https://openalex.org/W4385570646","https://openalex.org/W4385822954","https://openalex.org/W4385823321","https://openalex.org/W4386907505","https://openalex.org/W4402112053","https://openalex.org/W4405621913","https://openalex.org/W4408353935","https://openalex.org/W4408354509","https://openalex.org/W6631362777","https://openalex.org/W6755207826","https://openalex.org/W6801910562","https://openalex.org/W6805710207","https://openalex.org/W6853723667","https://openalex.org/W6856870961","https://openalex.org/W6857495872","https://openalex.org/W6874876819"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4389984014","https://openalex.org/W1940231550","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939","https://openalex.org/W2140022733","https://openalex.org/W2911612049"],"abstract_inverted_index":{"We":[0],"introduce":[1],"3D-Speaker-Toolkit,":[2,127],"an":[3],"open-source":[4,144],"toolkit":[5,138,156],"for":[6,13,133],"multimodal":[7,134],"speaker":[8,43,50,105,135],"verification":[9],"and":[10,20,33,58,73,121,147],"diarization,":[11],"designed":[12],"meeting":[14],"the":[15,27,71,80,102,114],"needs":[16],"of":[17,30,75,104,143],"academic":[18],"researchers":[19],"industrial":[21],"practitioners.":[22],"The":[23,46,62,89,137,155],"3D-Speaker-Toolkit":[24,115],"adeptly":[25],"leverages":[26,65],"combined":[28],"strengths":[29],"acoustic,":[31],"semantic,":[32],"visual":[34,90],"data,":[35],"seamlessly":[36],"fusing":[37],"these":[38,111],"modalities":[39],"to":[40,69,96,116],"offer":[41],"robust":[42],"recognition":[44],"capabilities.":[45],"acoustic":[47,53],"module":[48,64,91],"extracts":[49],"embeddings":[51],"from":[52],"features,":[54,99],"employing":[55],"both":[56],"fully-supervised":[57],"self-supervised":[59],"learning":[60],"approaches.":[61],"semantic":[63],"advanced":[66],"language":[67],"models":[68,146],"comprehend":[70],"substance":[72],"context":[74],"spoken":[76],"language,":[77],"thereby":[78],"augmenting":[79],"system\u2019s":[81],"proficiency":[82],"in":[83,107,123],"distinguishing":[84],"speakers":[85],"through":[86],"linguistic":[87],"patterns.":[88],"applies":[92],"image":[93],"processing":[94],"technologies":[95],"scrutinize":[97],"facial":[98],"which":[100],"bolsters":[101],"precision":[103],"diarization":[106],"multi-speaker":[108],"environments.":[109],"Collectively,":[110],"modules":[112],"empower":[113],"achieve":[117],"substantially":[118],"improved":[119],"accuracy":[120],"reliability":[122],"speaker-related":[124],"tasks.":[125],"With":[126],"we":[128],"establish":[129],"a":[130,141,148],"new":[131],"benchmark":[132],"analysis.":[136],"also":[139],"includes":[140],"handful":[142],"state-of-the-art":[145],"large-scale":[149],"dataset":[150],"containing":[151],"over":[152],"10,000":[153],"speakers.":[154],"is":[157],"publicly":[158],"available":[159],"at":[160],"https://github.com/modelscope/3D-Speaker.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}