{"id":"https://openalex.org/W4280634406","doi":"https://doi.org/10.21437/interspeech.2022-289","title":"PRISM: Pre-trained Indeterminate Speaker Representation Model for Speaker Diarization and Speaker Verification","display_name":"PRISM: Pre-trained Indeterminate Speaker Representation Model for Speaker Diarization and Speaker Verification","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4280634406","doi":"https://doi.org/10.21437/interspeech.2022-289"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-289","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-289","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5101700479","display_name":"Siqi Zheng","orcid":"https://orcid.org/0000-0002-5481-7900"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siqi Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109630497","display_name":"Hongbin Suo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongbin Suo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5026302891","display_name":"Qian Chen","orcid":"https://orcid.org/0000-0003-4406-5618"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"1431","last_page":"1435"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9776999950408936,"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":0.973800003528595,"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":0.9292886853218079},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7651083469390869},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7167191505432129},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.713005006313324},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6896241307258606},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5915811061859131},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5163551568984985},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4979405403137207},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47178906202316284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40043336153030396},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32162874937057495},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14291051030158997}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9292886853218079},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7651083469390869},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7167191505432129},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.713005006313324},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6896241307258606},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5915811061859131},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5163551568984985},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4979405403137207},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47178906202316284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40043336153030396},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32162874937057495},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14291051030158997},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-289","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-289","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"Speaker":[0],"embedding":[1],"has":[2],"been":[3],"a":[4,45,62,99],"fundamental":[5],"feature":[6],"for":[7,126],"speaker-related":[8],"tasks":[9,128],"such":[10,129],"as":[11,21,48,76,78,130],"verification,":[12,132],"clustering,":[13,134],"and":[14,135],"diarization.":[15,137],"Traditionally,":[16],"speaker":[17,46,63,100,106,131,133,136],"embeddings":[18],"are":[19,140],"represented":[20],"fixed":[22],"vectors":[23],"in":[24],"high-dimensional":[25],"space.":[26],"This":[27],"could":[28],"lead":[29],"to":[30,43,93],"biased":[31],"estimations,":[32],"especially":[33],"when":[34],"handling":[35],"shorter":[36],"utterances.":[37],"In":[38],"this":[39],"paper":[40],"we":[41],"propose":[42],"represent":[44],"utterance":[47,115],"\"floating\"":[49],"vector":[50],"whose":[51],"state":[52,60,97,112],"is":[53,65,82],"indeterminate":[54,105],"without":[55],"knowing":[56],"the":[57,73,89,95,111,118],"context.":[58,119],"The":[59,86,120],"of":[61,88,98,113],"representation":[64,107],"jointly":[66],"determined":[67],"by":[68],"itself,":[69],"other":[70,79],"speech":[71,90],"from":[72],"same":[74],"speaker,":[75],"well":[77],"speakers":[80],"it":[81],"being":[83],"compared":[84],"to.":[85],"content":[87],"also":[91],"contributes":[92],"determining":[94],"final":[96],"representation.":[101],"We":[102],"pre-train":[103],"an":[104,114],"model":[108,122],"that":[109],"estimates":[110],"based":[116],"on":[117],"pre-trained":[121],"can":[123],"be":[124],"fine-tuned":[125],"downstream":[127,144],"Substantial":[138],"improvements":[139],"observed":[141],"across":[142],"all":[143],"tasks.":[145]},"counts_by_year":[{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}