{"id":"https://openalex.org/W3163933965","doi":"https://doi.org/10.1109/icassp39728.2021.9413752","title":"Compositional Embedding Models for Speaker Identification and Diarization with Simultaneous Speech From 2+ Speakers","display_name":"Compositional Embedding Models for Speaker Identification and Diarization with Simultaneous Speech From 2+ Speakers","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163933965","doi":"https://doi.org/10.1109/icassp39728.2021.9413752","mag":"3163933965"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5044787071","display_name":"Zeqian Li","orcid":"https://orcid.org/0000-0002-0884-8028"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeqian Li","raw_affiliation_strings":["Worcester Polytechnic Institute (WPI),Massachusetts,USA","Worcester Polytechnic Institute (WPI), Massachusetts, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute (WPI),Massachusetts,USA","institution_ids":["https://openalex.org/I107077323"]},{"raw_affiliation_string":"Worcester Polytechnic Institute (WPI), Massachusetts, USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027788582","display_name":"Jacob Whitehill","orcid":"https://orcid.org/0000-0002-5851-312X"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Whitehill","raw_affiliation_strings":["Worcester Polytechnic Institute (WPI),Massachusetts,USA","Worcester Polytechnic Institute (WPI), Massachusetts, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute (WPI),Massachusetts,USA","institution_ids":["https://openalex.org/I107077323"]},{"raw_affiliation_string":"Worcester Polytechnic Institute (WPI), Massachusetts, USA","institution_ids":["https://openalex.org/I107077323"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I107077323"],"apc_list":null,"apc_paid":null,"fwci":0.5861,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.66986315,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7163","last_page":"7167"},"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":0.9994000196456909,"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":0.9994000196456909,"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":0.8683673143386841},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7928577661514282},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7342110872268677},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6822221279144287},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6062179803848267},{"id":"https://openalex.org/keywords/headset","display_name":"Headset","score":0.5256044864654541},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5226224064826965},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.4731244444847107},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4605492949485779},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44608113169670105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3622680604457855},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07071426510810852}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8683673143386841},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7928577661514282},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7342110872268677},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6822221279144287},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6062179803848267},{"id":"https://openalex.org/C2780657452","wikidata":"https://www.wikidata.org/wiki/Q1193170","display_name":"Headset","level":2,"score":0.5256044864654541},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5226224064826965},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.4731244444847107},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4605492949485779},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44608113169670105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3622680604457855},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07071426510810852},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W191366985","https://openalex.org/W1494198834","https://openalex.org/W1992106273","https://openalex.org/W2046056978","https://openalex.org/W2083751884","https://openalex.org/W2096733369","https://openalex.org/W2106053110","https://openalex.org/W2114970513","https://openalex.org/W2219249508","https://openalex.org/W2408021097","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2889203268","https://openalex.org/W2890964092","https://openalex.org/W2917792613","https://openalex.org/W2962788625","https://openalex.org/W2964052309","https://openalex.org/W2972949456","https://openalex.org/W3015780472","https://openalex.org/W3015783745","https://openalex.org/W3099206234","https://openalex.org/W3119727976","https://openalex.org/W6675751002","https://openalex.org/W6687442591","https://openalex.org/W6688816777","https://openalex.org/W6773808957"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4403618900","https://openalex.org/W36105149","https://openalex.org/W2545131480","https://openalex.org/W4401661962","https://openalex.org/W4247736853","https://openalex.org/W1521049138","https://openalex.org/W2997340161","https://openalex.org/W1589374915","https://openalex.org/W2136038945"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,37,50,104],"new":[3],"method":[4,17,87],"for":[5],"speaker":[6,26,79,101,105],"diarization":[7,106],"that":[8,40,92],"can":[9],"handle":[10],"overlapping":[11],"speech":[12,42],"with":[13],"2+":[14],"people.":[15],"Our":[16],"is":[18],"based":[19],"on":[20,77,108],"compositional":[21,33],"embeddings":[22],"[1]:":[23],"Like":[24],"standard":[25],"embedding":[27,34,60,90],"methods":[28,91],"such":[29],"as":[30,63],"x-vector":[31],"[2],":[32],"models":[35],"contain":[36],"function":[38,52],"f":[39],"separates":[41],"from":[43,127],"different":[44],"speakers.":[45],"In":[46,74,103],"addition,":[47],"they":[48],"include":[49],"composition":[51],"g":[53],"to":[54,64,96],"compute":[55],"set-union":[56],"operations":[57],"in":[58],"the":[59,66,71,85,109,122],"space":[61],"so":[62],"infer":[65],"set":[67],"of":[68],"speakers":[69,99],"within":[70],"input":[72],"audio.":[73],"an":[75],"experiment":[76,107],"multi-person":[78],"identification":[80],"using":[81],"synthesized":[82],"LibriSpeech":[83],"data,":[84],"proposed":[86],"outperforms":[88],"traditional":[89],"are":[93],"only":[94],"trained":[95],"separate":[97],"single":[98],"(not":[100],"sets).":[102],"AMI":[110],"Headset":[111],"Mix":[112],"corpus,":[113],"we":[114],"achieve":[115],"state-of-the-art":[116],"accuracy":[117],"(DER=22.93%),":[118],"slightly":[119],"better":[120],"than":[121],"previous":[123],"best":[124],"result":[125],"(23.82%":[126],"[3]).":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}