{"id":"https://openalex.org/W2985913104","doi":"https://doi.org/10.1109/icassp40776.2020.9052974","title":"Pyannote.Audio: Neural Building Blocks for Speaker Diarization","display_name":"Pyannote.Audio: Neural Building Blocks for Speaker Diarization","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2985913104","doi":"https://doi.org/10.1109/icassp40776.2020.9052974","mag":"2985913104"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9052974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9052974","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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1911.01255","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079257674","display_name":"Herv\u00e9 Bredin","orcid":"https://orcid.org/0000-0002-3739-925X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Herve Bredin","raw_affiliation_strings":["github.com/pyannote/pyannote-audio"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"github.com/pyannote/pyannote-audio","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090981476","display_name":"Ruiqing Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruiqing Yin","raw_affiliation_strings":["github.com/pyannote/pyannote-audio"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"github.com/pyannote/pyannote-audio","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017320570","display_name":"Juan Manuel Coria","orcid":"https://orcid.org/0000-0002-5035-147X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juan Manuel Coria","raw_affiliation_strings":["github.com/pyannote/pyannote-audio"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"github.com/pyannote/pyannote-audio","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087187781","display_name":"Gr\u00e9gory Gelly","orcid":"https://orcid.org/0000-0003-3402-2446"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gregory Gelly","raw_affiliation_strings":["github.com/pyannote/pyannote-audio"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"github.com/pyannote/pyannote-audio","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024538974","display_name":"Pavel Korshunov","orcid":"https://orcid.org/0000-0002-2244-1830"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pavel Korshunov","raw_affiliation_strings":["github.com/pyannote/pyannote-audio"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"github.com/pyannote/pyannote-audio","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057205161","display_name":"Marvin Lavechin","orcid":"https://orcid.org/0000-0002-6005-9368"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marvin Lavechin","raw_affiliation_strings":["github.com/pyannote/pyannote-audio"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"github.com/pyannote/pyannote-audio","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075104449","display_name":"Diego Fustes","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Diego Fustes","raw_affiliation_strings":["github.com/pyannote/pyannote-audio"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"github.com/pyannote/pyannote-audio","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005882992","display_name":"Hadrien Titeux","orcid":"https://orcid.org/0000-0002-8511-1644"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hadrien Titeux","raw_affiliation_strings":["github.com/pyannote/pyannote-audio"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"github.com/pyannote/pyannote-audio","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008995133","display_name":"Wassim Bouaziz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wassim Bouaziz","raw_affiliation_strings":["github.com/pyannote/pyannote-audio"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"github.com/pyannote/pyannote-audio","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069581526","display_name":"Marie-Philippe Gill","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marie-Philippe Gill","raw_affiliation_strings":["github.com/pyannote/pyannote-audio"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"github.com/pyannote/pyannote-audio","institution_ids":[]}]}],"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":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7124","last_page":"7128"},"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":0.9990000128746033,"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":0.9984999895095825,"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":0.9228586554527283},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7889114618301392},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6691246032714844},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.6283871531486511},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5988701581954956},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.584141194820404},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49345293641090393},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.48806774616241455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30706512928009033}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9228586554527283},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7889114618301392},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6691246032714844},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6283871531486511},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5988701581954956},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.584141194820404},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49345293641090393},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.48806774616241455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30706512928009033},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/icassp40776.2020.9052974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9052974","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"},{"id":"pmh:oai:arXiv.org:1911.01255","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.01255","pdf_url":"https://arxiv.org/pdf/1911.01255","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":"text"},{"id":"mag:2985913104","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1911.01255v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:HAL:hal-02995345v1","is_oa":false,"landing_page_url":"https://hal.science/hal-02995345","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech, and Signal Processing, May 2020, Barcelona, Spain. pp.7124-7128, ⟨10.1109/ICASSP40776.2020.9052974⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:infoscience.epfl.ch:277696","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/277696","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/277696","raw_type":"Text"},{"id":"doi:10.48550/arxiv.1911.01255","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1911.01255","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/e2sv-1518","is_oa":true,"landing_page_url":"https://doi.org/10.17023/e2sv-1518","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1911.01255","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.01255","pdf_url":"https://arxiv.org/pdf/1911.01255","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2116133628","display_name":"ComPLetely Unsupervised Multimodal Character identification On TV series and movies","funder_award_id":"ANR-16-CE92-0025","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G3890051348","display_name":"Online Diarization Enhanced by recent Speaker identification and Sequential learning Approaches","funder_award_id":"ANR-15-CE39-0010","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W72302491","https://openalex.org/W1524333225","https://openalex.org/W2009876684","https://openalex.org/W2083751884","https://openalex.org/W2097470427","https://openalex.org/W2192412620","https://openalex.org/W2746241180","https://openalex.org/W2750259098","https://openalex.org/W2767895109","https://openalex.org/W2808631503","https://openalex.org/W2889203268","https://openalex.org/W2889233255","https://openalex.org/W2890964092","https://openalex.org/W2891247151","https://openalex.org/W2964052309","https://openalex.org/W2968071640","https://openalex.org/W2972449503","https://openalex.org/W2972680151","https://openalex.org/W3015780472","https://openalex.org/W6602944679","https://openalex.org/W6631362777"],"related_works":["https://openalex.org/W3015783745","https://openalex.org/W3016031604","https://openalex.org/W2063511145","https://openalex.org/W2992261503","https://openalex.org/W2890825077","https://openalex.org/W1658556320","https://openalex.org/W2144375099","https://openalex.org/W2963470929","https://openalex.org/W2991553872","https://openalex.org/W3178100380","https://openalex.org/W317426935","https://openalex.org/W2901404901","https://openalex.org/W2165706241","https://openalex.org/W2736195796","https://openalex.org/W2052269122","https://openalex.org/W3212278860","https://openalex.org/W1975884129","https://openalex.org/W2968071640","https://openalex.org/W3094005623","https://openalex.org/W103362674"],"abstract_inverted_index":{"We":[0],"introduce":[1],"pyannote.audio,":[2],"an":[3],"open-source":[4],"toolkit":[5],"written":[6],"in":[7],"Python":[8],"for":[9,52,69],"speaker":[10,37,56,63],"diarization.":[11],"Based":[12],"on":[13],"PyTorch":[14],"machine":[15],"learning":[16],"framework,":[17],"it":[18],"provides":[19],"a":[20,47],"set":[21],"of":[22,50,71],"trainable":[23],"end-to-end":[24],"neural":[25],"building":[26],"blocks":[27],"that":[28],"can":[29],"be":[30],"combined":[31],"and":[32,62],"jointly":[33],"optimized":[34],"to":[35],"build":[36],"diarization":[38],"pipelines.":[39],"pyannote.audio":[40],"also":[41],"comes":[42],"with":[43],"pre-trained":[44],"models":[45],"covering":[46],"wide":[48],"range":[49],"domains":[51],"voice":[53],"activity":[54],"detection,":[55,58,61],"change":[57],"overlapped":[59],"speech":[60],"embedding":[64],"-":[65],"reaching":[66],"state-of-the-art":[67],"performance":[68],"most":[70],"them.":[72]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}