{"id":"https://openalex.org/W3015988545","doi":"https://doi.org/10.1109/icassp40776.2020.9054273","title":"Speaker Embeddings Incorporating Acoustic Conditions for Diarization","display_name":"Speaker Embeddings Incorporating Acoustic Conditions for Diarization","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015988545","doi":"https://doi.org/10.1109/icassp40776.2020.9054273","mag":"3015988545"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054273","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":"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/A5102017467","display_name":"Yosuke Higuchi","orcid":"https://orcid.org/0000-0003-4500-8957"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yosuke Higuchi","raw_affiliation_strings":["IBM Research AI, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028421346","display_name":"Masayuki Suzuki","orcid":"https://orcid.org/0000-0002-0436-1490"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masayuki Suzuki","raw_affiliation_strings":["IBM Research AI, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021294422","display_name":"Gakuto Kurata","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Gakuto Kurata","raw_affiliation_strings":["IBM Research AI, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210145865"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7129","last_page":"7133"},"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":0.9994999766349792,"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":0.9258352518081665},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7639434337615967},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7483946681022644},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6455103754997253},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6230279803276062},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.5727496147155762},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5072571635246277},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.46423426270484924},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.44732803106307983},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3163515329360962},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10191917419433594},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06067293882369995}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9258352518081665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7639434337615967},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7483946681022644},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6455103754997253},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6230279803276062},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.5727496147155762},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5072571635246277},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.46423426270484924},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.44732803106307983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3163515329360962},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10191917419433594},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06067293882369995},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/icassp40776.2020.9054273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054273","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":[{"score":0.7099999785423279,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2038101708","https://openalex.org/W2046056978","https://openalex.org/W2064675550","https://openalex.org/W2081074144","https://openalex.org/W2114925438","https://openalex.org/W2150769028","https://openalex.org/W2159591770","https://openalex.org/W2405137844","https://openalex.org/W2584329820","https://openalex.org/W2638067502","https://openalex.org/W2726515241","https://openalex.org/W2746574320","https://openalex.org/W2808631503","https://openalex.org/W2888968865","https://openalex.org/W2890964092","https://openalex.org/W2899771611","https://openalex.org/W2962788625","https://openalex.org/W2963470929","https://openalex.org/W2963702081","https://openalex.org/W2969985801","https://openalex.org/W2972949456","https://openalex.org/W2973127116","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1977167953","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863"],"abstract_inverted_index":{"We":[0],"present":[1],"our":[2],"work":[3],"on":[4,108,129,146],"training":[5],"speaker":[6,11,15,19,49,81,101,104],"embeddings,":[7],"especially":[8],"effective":[9,100],"for":[10,61,79,103,121],"diarization.":[12,105],"For":[13],"various":[14],"recognition":[16],"tasks,":[17],"extracting":[18],"embeddings":[20,31,102,138,143],"using":[21,125],"Deep":[22],"Neural":[23],"Networks":[24],"(DNNs)":[25],"has":[26],"become":[27],"major":[28],"methods.":[29],"These":[30],"are":[32],"generally":[33],"trained":[34],"to":[35,44,70,98,116],"be":[36,40,56,112],"discriminate":[37],"speakers":[38],"and":[39],"robust":[41],"with":[42],"respect":[43],"different":[45],"acoustic":[46,53,96,109,147],"conditions.":[47,148],"In":[48],"diarization,":[50],"however,":[51],"the":[52,68,77,89,136],"conditions":[54,97,110],"can":[55,66,111],"used":[57],"as":[58],"consistent":[59],"information":[60,65,107,145],"discriminating":[62],"speakers.":[63],"Such":[64],"include":[67],"distances":[69],"a":[71,74,130],"microphone":[72],"in":[73,82,86,95],"meeting,":[75],"or":[76],"channels":[78],"each":[80],"telephone":[83],"conversation":[84],"recorded":[85],"monaural.":[87],"Hence,":[88],"proposed":[90,137],"speaker-embedding":[91],"network":[92],"leverages":[93],"differences":[94],"train":[99],"The":[106],"anything":[113],"that":[114,135],"contributes":[115],"distinguishing":[117],"between":[118],"recording":[119],"environments;":[120],"example,":[122],"we":[123],"explore":[124],"i-vectors.":[126],"Experiments":[127],"conducted":[128],"practical":[131],"diarization":[132],"system":[133],"demonstrated":[134],"significantly":[139],"improve":[140],"performance":[141],"over":[142],"without":[144]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}