{"id":"https://openalex.org/W4402112220","doi":"https://doi.org/10.21437/interspeech.2024-1060","title":"On the calibration of powerset speaker diarization models","display_name":"On the calibration of powerset speaker diarization models","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112220","doi":"https://doi.org/10.21437/interspeech.2024-1060"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-1060","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-1060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.15885","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092639568","display_name":"Alexis Plaquet","orcid":null},"institutions":[{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555"]},{"id":"https://openalex.org/I3131550300","display_name":"Universit\u00e9 Toulouse-I-Capitole","ror":"https://ror.org/0443n9e75","country_code":"FR","type":"education","lineage":["https://openalex.org/I3131550300"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4405258862","https://openalex.org/I4405259414"]},{"id":"https://openalex.org/I4210152422","display_name":"Universit\u00e9 Toulouse - Jean Jaur\u00e8s","ror":"https://ror.org/04ezk3x31","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210152422"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Alexis Plaquet","raw_affiliation_strings":["IRIT-SAMoVA - \u00c9quipe Structuration, Analyse et MOd\u00e9lisation de documents Vid\u00e9o et Audio (IRIT\r\n118 Route de Narbonne\r\n31062 Toulouse Cedex 9 - France)","UT3 - Universit\u00e9 Toulouse III - Paul Sabatier (118 route de Narbonne - 31062 Toulouse - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IRIT-SAMoVA - \u00c9quipe Structuration, Analyse et MOd\u00e9lisation de documents Vid\u00e9o et Audio (IRIT\r\n118 Route de Narbonne\r\n31062 Toulouse Cedex 9 - France)","institution_ids":["https://openalex.org/I134560555","https://openalex.org/I3131550300","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4210160189"]},{"raw_affiliation_string":"UT3 - Universit\u00e9 Toulouse III - Paul Sabatier (118 route de Narbonne - 31062 Toulouse - France)","institution_ids":["https://openalex.org/I134560555"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079257674","display_name":"Herv\u00e9 Bredin","orcid":"https://orcid.org/0000-0002-3739-925X"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555"]},{"id":"https://openalex.org/I3131550300","display_name":"Universit\u00e9 Toulouse-I-Capitole","ror":"https://ror.org/0443n9e75","country_code":"FR","type":"education","lineage":["https://openalex.org/I3131550300"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4405258862","https://openalex.org/I4405259414"]},{"id":"https://openalex.org/I4210152422","display_name":"Universit\u00e9 Toulouse - Jean Jaur\u00e8s","ror":"https://ror.org/04ezk3x31","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210152422"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Herv\u00e9 Bredin","raw_affiliation_strings":["CNRS - Centre National de la Recherche Scientifique (France)","IRIT-SAMoVA - \u00c9quipe Structuration, Analyse et MOd\u00e9lisation de documents Vid\u00e9o et Audio (IRIT\r\n118 Route de Narbonne\r\n31062 Toulouse Cedex 9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS - Centre National de la Recherche Scientifique (France)","institution_ids":["https://openalex.org/I1294671590"]},{"raw_affiliation_string":"IRIT-SAMoVA - \u00c9quipe Structuration, Analyse et MOd\u00e9lisation de documents Vid\u00e9o et Audio (IRIT\r\n118 Route de Narbonne\r\n31062 Toulouse Cedex 9 - France)","institution_ids":["https://openalex.org/I134560555","https://openalex.org/I3131550300","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4210160189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13494298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3764","last_page":"3768"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9976999759674072,"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/T10028","display_name":"Topic Modeling","score":0.9966999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.77347731590271},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.6795358061790466},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5465410351753235},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5371068120002747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5351451635360718},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5183092951774597},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5159793496131897},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4404500126838684},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.41638824343681335},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3705567717552185},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34231212735176086},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3422425389289856},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3316989541053772},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.23533278703689575},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14651080965995789},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11190199851989746}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.77347731590271},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.6795358061790466},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5465410351753235},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5371068120002747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5351451635360718},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5183092951774597},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5159793496131897},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4404500126838684},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.41638824343681335},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3705567717552185},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34231212735176086},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3422425389289856},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3316989541053772},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.23533278703689575},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14651080965995789},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11190199851989746},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2024-1060","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-1060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2409.15885","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.15885","pdf_url":"https://arxiv.org/pdf/2409.15885","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-04696316v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04696316","pdf_url":"https://hal.science/hal-04696316v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"25th Interspeech Conference (INTERSPEECH 2024), ISCA: International Speech Communication Association, Sep 2024, Kos, Greece. pp.3764--3768, ⟨10.21437/Interspeech.2024-1060⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.15885","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.15885","pdf_url":"https://arxiv.org/pdf/2409.15885","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320326256","display_name":"Grand \u00c9quipement National De Calcul Intensif","ror":"https://ror.org/0010d1q40"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402112220.pdf","grobid_xml":"https://content.openalex.org/works/W4402112220.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W135211875","https://openalex.org/W2052269122","https://openalex.org/W2625833328","https://openalex.org/W4389272081"],"abstract_inverted_index":{"End-to-end":[0],"neural":[1],"diarization":[2,14,44],"models":[3],"have":[4],"usually":[5],"relied":[6],"on":[7,28,118,128],"a":[8,19,41,122],"multilabel-classification":[9],"formulation":[10,22],"of":[11,40,49,70,82,94],"the":[12,26,38,54,63,80,83],"speaker":[13,43],"problem.":[15],"Recently,":[16],"we":[17,34,78],"proposed":[18],"powerset":[20,42],"multiclass":[21],"that":[23,105],"has":[24],"beaten":[25],"state-of-the-art":[27],"multiple":[29],"datasets.":[30],"In":[31],"this":[32,99],"paper,":[33],"propose":[35],"to":[36,86,100,111],"study":[37,53],"calibration":[39,55],"model,":[45,125],"and":[46,61,90,97,126],"explore":[47,62],"some":[48],"its":[50],"uses.":[51],"We":[52,103],"in-domain,":[56],"as":[57,59],"well":[58],"out-of-domain,":[60],"data":[64],"in":[65,76],"low-confidence":[66,119,129],"regions.":[67,115,137],"The":[68],"reliability":[69],"model":[71,85],"confidence":[72,81,107],"is":[73],"then":[74],"tested":[75],"practice:":[77],"use":[79],"pretrained":[84],"selectively":[87],"create":[88],"training":[89,117],"validation":[91],"subsets":[92],"out":[93],"unannotated":[95],"data,":[96],"compare":[98],"random":[101,136],"selection.":[102],"find":[104],"top-label":[106],"can":[108,131],"be":[109,132],"used":[110],"reliably":[112],"predict":[113],"high-error":[114],"Moreover,":[116],"regions":[120,130],"provides":[121],"better":[123],"calibrated":[124],"validating":[127],"more":[133],"annotation-efficient":[134],"than":[135]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}