{"id":"https://openalex.org/W4296070207","doi":"https://doi.org/10.21437/interspeech.2022-10605","title":"Unsupervised Speaker Diarization that is Agnostic to Language, Overlap-Aware, and Tuning Free","display_name":"Unsupervised Speaker Diarization that is Agnostic to Language, Overlap-Aware, and Tuning Free","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296070207","doi":"https://doi.org/10.21437/interspeech.2022-10605"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10605","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10605","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":"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/A5018690901","display_name":"Md Iftekhar Tanveer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122154","display_name":"Photon Spot (United States)","ror":"https://ror.org/01yxc0v75","country_code":"US","type":"company","lineage":["https://openalex.org/I4210122154"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Md Iftekhar Tanveer","raw_affiliation_strings":["Spotify, USA &"],"affiliations":[{"raw_affiliation_string":"Spotify, USA &","institution_ids":["https://openalex.org/I4210122154"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069700219","display_name":"Diego Casabuena","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122154","display_name":"Photon Spot (United States)","ror":"https://ror.org/01yxc0v75","country_code":"US","type":"company","lineage":["https://openalex.org/I4210122154"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Diego Casabuena","raw_affiliation_strings":["Spotify, USA &"],"affiliations":[{"raw_affiliation_string":"Spotify, USA &","institution_ids":["https://openalex.org/I4210122154"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001872735","display_name":"Jussi Karlgren","orcid":"https://orcid.org/0000-0003-4042-4919"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jussi Karlgren","raw_affiliation_strings":["Spotify, Sweden"],"affiliations":[{"raw_affiliation_string":"Spotify, Sweden","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000992993","display_name":"Rosie Jones","orcid":"https://orcid.org/0009-0000-3821-1207"},"institutions":[{"id":"https://openalex.org/I4210122154","display_name":"Photon Spot (United States)","ror":"https://ror.org/01yxc0v75","country_code":"US","type":"company","lineage":["https://openalex.org/I4210122154"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rosie Jones","raw_affiliation_strings":["Spotify, USA &"],"affiliations":[{"raw_affiliation_string":"Spotify, USA &","institution_ids":["https://openalex.org/I4210122154"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5018690901"],"corresponding_institution_ids":["https://openalex.org/I4210122154"],"apc_list":null,"apc_paid":null,"fwci":0.7276,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.71310062,"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":"1481","last_page":"1485"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9993000030517578,"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":0.9986000061035156,"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":0.7648893594741821},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7113653421401978},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5493268370628357},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39374056458473206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3829965591430664},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3374137580394745}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7648893594741821},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7113653421401978},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5493268370628357},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39374056458473206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3829965591430664},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3374137580394745}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10605","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10605","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W48568691","https://openalex.org/W1522301498","https://openalex.org/W2015418199","https://openalex.org/W2038101708","https://openalex.org/W2058760524","https://openalex.org/W2097749765","https://openalex.org/W2100556411","https://openalex.org/W2114925438","https://openalex.org/W2115599677","https://openalex.org/W2136745572","https://openalex.org/W2150769028","https://openalex.org/W2164452299","https://openalex.org/W2168025753","https://openalex.org/W2169264834","https://openalex.org/W2402428045","https://openalex.org/W2885918317","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2896538040","https://openalex.org/W2963470929","https://openalex.org/W2973127116","https://openalex.org/W2981087920","https://openalex.org/W3008357631","https://openalex.org/W3015780472","https://openalex.org/W3015783745","https://openalex.org/W3038871978","https://openalex.org/W3095822285","https://openalex.org/W3113822960","https://openalex.org/W3140898556","https://openalex.org/W3147642179","https://openalex.org/W3152994072","https://openalex.org/W3212886388","https://openalex.org/W4297775537"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"Podcasts":[0],"are":[1,8],"conversational":[2],"in":[3],"nature":[4],"and":[5,30],"speaker":[6,10,20],"changes":[7],"frequent-requiring":[9],"diarization":[11,21],"for":[12,19],"content":[13],"understanding.We":[14],"propose":[15],"an":[16],"unsupervised":[17],"technique":[18],"without":[22],"relying":[23],"on":[24,44,48,56],"language-specific":[25],"components.The":[26],"algorithm":[27],"is":[28],"overlap-aware":[29],"does":[31],"not":[32],"require":[33],"information":[34],"about":[35],"the":[36,51],"number":[37],"of":[38],"speakers.Our":[39],"approach":[40],"shows":[41],"79%":[42],"improvement":[43],"purity":[45],"scores":[46],"(34%":[47],"F-score)":[49],"against":[50],"Google":[52],"Cloud":[53],"Platform":[54],"solution":[55],"podcast":[57],"data.":[58]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
