{"id":"https://openalex.org/W3015621653","doi":"https://doi.org/10.1109/icassp40776.2020.9053122","title":"Multimodal Speaker Diarization of Real-World Meetings Using D-Vectors With Spatial Features","display_name":"Multimodal Speaker Diarization of Real-World Meetings Using D-Vectors With Spatial Features","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015621653","doi":"https://doi.org/10.1109/icassp40776.2020.9053122","mag":"3015621653"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5052061361","display_name":"Wonjune Kang","orcid":"https://orcid.org/0000-0001-5260-9094"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wonjune Kang","raw_affiliation_strings":["Massachusetts Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040787249","display_name":"Brandon Roy","orcid":"https://orcid.org/0009-0002-6739-203X"},"institutions":[{"id":"https://openalex.org/I4210142372","display_name":"Human Media","ror":"https://ror.org/04072nk43","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210142372"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brandon C. Roy","raw_affiliation_strings":["MIT Media Lab, USA"],"affiliations":[{"raw_affiliation_string":"MIT Media Lab, USA","institution_ids":["https://openalex.org/I4210142372"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052120713","display_name":"Wesley Chow","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142372","display_name":"Human Media","ror":"https://ror.org/04072nk43","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210142372"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wesley Chow","raw_affiliation_strings":["MIT Media Lab, USA"],"affiliations":[{"raw_affiliation_string":"MIT Media Lab, USA","institution_ids":["https://openalex.org/I4210142372"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052061361"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":1.8558,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.88251279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6509","last_page":"6513"},"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":0.9998000264167786,"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":0.9995999932289124,"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":0.9086222052574158},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7842357754707336},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6681879162788391},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6276777982711792},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6125688552856445},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5913833379745483},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.542864203453064},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5038480162620544},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44536980986595154},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4279053509235382},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4059518575668335},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39043182134628296},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2663125693798065},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1085137128829956}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9086222052574158},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7842357754707336},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6681879162788391},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6276777982711792},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6125688552856445},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5913833379745483},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.542864203453064},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5038480162620544},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44536980986595154},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4279053509235382},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4059518575668335},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39043182134628296},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2663125693798065},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1085137128829956},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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":29,"referenced_works":["https://openalex.org/W48568691","https://openalex.org/W126779258","https://openalex.org/W1569447338","https://openalex.org/W1606894530","https://openalex.org/W1965819578","https://openalex.org/W2038101708","https://openalex.org/W2049893888","https://openalex.org/W2081074144","https://openalex.org/W2115599677","https://openalex.org/W2148613904","https://openalex.org/W2153842971","https://openalex.org/W2153994037","https://openalex.org/W2394699868","https://openalex.org/W2638067502","https://openalex.org/W2726515241","https://openalex.org/W2796898951","https://openalex.org/W2805869973","https://openalex.org/W2808631503","https://openalex.org/W2889031312","https://openalex.org/W2890964092","https://openalex.org/W2896538040","https://openalex.org/W2938358845","https://openalex.org/W2962788625","https://openalex.org/W2963470929","https://openalex.org/W2972729214","https://openalex.org/W6601947329","https://openalex.org/W6633847657","https://openalex.org/W6682965620","https://openalex.org/W6712079985"],"related_works":["https://openalex.org/W1963976507","https://openalex.org/W2206035908","https://openalex.org/W3119288895","https://openalex.org/W1879255185","https://openalex.org/W1977167953","https://openalex.org/W2185075503","https://openalex.org/W2769861442","https://openalex.org/W2162158162","https://openalex.org/W2120442551","https://openalex.org/W1980506188"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"network":[2],"based":[3],"audio":[4],"embeddings":[5,83],"(d-vectors)":[6],"have":[7],"demonstrated":[8],"superior":[9],"performance":[10],"in":[11],"audio-only":[12],"speaker":[13,56,82],"diarization":[14,36,57,143],"compared":[15],"to":[16,54,135],"traditional":[17],"acoustic":[18,117],"features":[19,86,120],"such":[20],"as":[21],"mel-frequency":[22],"cepstral":[23],"coefficients":[24],"(MFCCs)":[25],"and":[26,84,107,118,132],"i-vectors.":[27],"However,":[28],"there":[29],"has":[30],"been":[31],"little":[32],"work":[33],"on":[34,78,102],"multimodal":[35,55,142],"systems":[37],"that":[38,58,87],"combine":[39],"dvectors":[40],"with":[41,61,139],"additional":[42],"sources":[43],"of":[44,81,111],"information.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49,123],"present":[50],"a":[51,69,79,128],"novel":[52],"approach":[53],"combines":[59],"d-vectors":[60],"spatial":[62,85,119],"information":[63],"derived":[64],"from":[65],"performing":[66],"beamforming":[67],"given":[68],"multi-channel":[70],"microphone":[71],"array.":[72],"Our":[73],"system":[74,101],"performs":[75],"spectral":[76],"clustering":[77],"combination":[80],"are":[88],"computed":[89],"using":[90,115],"the":[91,103],"Steered-Response":[92],"Power":[93],"Phase":[94],"Transform":[95],"(SRP-PHAT)":[96],"algorithm.":[97],"We":[98],"evaluate":[99],"our":[100],"AMI":[104],"Meeting":[105],"Corpus":[106],"an":[108],"internal":[109],"dataset":[110],"real-world":[112],"conversations.":[113],"By":[114],"both":[116],"for":[121],"diarization,":[122],"achieve":[124,136],"significant":[125],"improvements":[126],"over":[127],"dvector":[129],"only":[130],"baseline":[131],"show":[133],"potential":[134],"comparable":[137],"results":[138],"other":[140],"state-of-the-art":[141],"systems.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}