{"id":"https://openalex.org/W2739041555","doi":"https://doi.org/10.1109/waspaa.2017.8169991","title":"Exploiting the intermittency of speech for joint separation and diarization","display_name":"Exploiting the intermittency of speech for joint separation and diarization","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2739041555","doi":"https://doi.org/10.1109/waspaa.2017.8169991","mag":"2739041555"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa.2017.8169991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2017.8169991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-01568813","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041055085","display_name":"Dionyssos Kounades-Bastian","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Dionyssos Kounades-Bastian","raw_affiliation_strings":["INRIA Grenoble Rh\u00f4ne-Alpes, France","PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rh\u00f4ne-Alpes, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020392160","display_name":"Laurent Girin","orcid":"https://orcid.org/0000-0002-9214-8760"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"id":"https://openalex.org/I4210124956","display_name":"GIPSA-Lab","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laurent Girin","raw_affiliation_strings":["INRIA Grenoble Rh\u00f4ne-Alpes, France","Univ. Grenoble Alpes, GIPSA-lab, France","PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)","GIPSA-CRISSP - GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rh\u00f4ne-Alpes, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Univ. Grenoble Alpes, GIPSA-lab, France","institution_ids":["https://openalex.org/I4210124956","https://openalex.org/I899635006"]},{"raw_affiliation_string":"PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"raw_affiliation_string":"GIPSA-CRISSP - GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)","institution_ids":["https://openalex.org/I4210124956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066621495","display_name":"Xavier Alameda-Pineda","orcid":"https://orcid.org/0000-0002-5354-1084"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Xavier Alameda-Pineda","raw_affiliation_strings":["INRIA Grenoble Rh\u00f4ne-Alpes, France","PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rh\u00f4ne-Alpes, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078307335","display_name":"Radu Horaud","orcid":"https://orcid.org/0000-0001-5232-024X"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Radu Horaud","raw_affiliation_strings":["INRIA Grenoble Rh\u00f4ne-Alpes, France","PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rh\u00f4ne-Alpes, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001052072","display_name":"Sharon Gannot","orcid":"https://orcid.org/0000-0002-2885-170X"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Sharon Gannot","raw_affiliation_strings":["Faculty of Engineering, Bar-Ilan University, Israel","Bar-Ilan University [Isra\u00ebl] (Ramat-Gan 5290002,\r\nIsrael - Israel)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Bar-Ilan University, Israel","institution_ids":["https://openalex.org/I13955877"]},{"raw_affiliation_string":"Bar-Ilan University [Isra\u00ebl] (Ramat-Gan 5290002,\r\nIsrael - Israel)","institution_ids":["https://openalex.org/I13955877"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":null,"first_page":"41","last_page":"45"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":0.9991000294685364,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9958999752998352,"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":0.6844726800918579},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6835157871246338},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6464263796806335},{"id":"https://openalex.org/keywords/intermittency","display_name":"Intermittency","score":0.6354637145996094},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5791630744934082},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5545816421508789},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5260006189346313},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.46579110622406006},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.4572661817073822},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.429691344499588},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4225442111492157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3206721246242523},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2274927794933319},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1569942831993103},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14320522546768188},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12044143676757812},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10739800333976746},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.09821978211402893}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6844726800918579},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6835157871246338},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6464263796806335},{"id":"https://openalex.org/C2780388094","wikidata":"https://www.wikidata.org/wiki/Q1666248","display_name":"Intermittency","level":3,"score":0.6354637145996094},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5791630744934082},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5545816421508789},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5260006189346313},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.46579110622406006},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.4572661817073822},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.429691344499588},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4225442111492157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3206721246242523},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2274927794933319},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1569942831993103},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14320522546768188},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12044143676757812},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10739800333976746},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.09821978211402893},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C196558001","wikidata":"https://www.wikidata.org/wiki/Q190132","display_name":"Turbulence","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/waspaa.2017.8169991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2017.8169991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01568813v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01568813","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WASPAA 2017 - IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, Oct 2017, New Paltz, NY, United States. pp.41-45, ⟨10.1109/WASPAA.2017.8169991⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01568813v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01568813","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WASPAA 2017 - IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, Oct 2017, New Paltz, NY, United States. pp.41-45, ⟨10.1109/WASPAA.2017.8169991⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1604165404","https://openalex.org/W1663973292","https://openalex.org/W1755563775","https://openalex.org/W1819025208","https://openalex.org/W1965279578","https://openalex.org/W1967504554","https://openalex.org/W2039844283","https://openalex.org/W2069748678","https://openalex.org/W2081074144","https://openalex.org/W2098918476","https://openalex.org/W2104298926","https://openalex.org/W2111493103","https://openalex.org/W2113990625","https://openalex.org/W2117332620","https://openalex.org/W2135104405","https://openalex.org/W2143027228","https://openalex.org/W2155531311","https://openalex.org/W2218653417","https://openalex.org/W2278526211","https://openalex.org/W2283599234","https://openalex.org/W2316138215","https://openalex.org/W2470294693","https://openalex.org/W2528361532","https://openalex.org/W2568308529","https://openalex.org/W2607290939","https://openalex.org/W2607334104","https://openalex.org/W2611465255","https://openalex.org/W3127686677","https://openalex.org/W4212863985","https://openalex.org/W6636245779","https://openalex.org/W6638560928","https://openalex.org/W6677083428","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W2564644595","https://openalex.org/W1566002589","https://openalex.org/W1589804082","https://openalex.org/W2042838258","https://openalex.org/W4226166178","https://openalex.org/W2783018065","https://openalex.org/W1525560163","https://openalex.org/W1967480872","https://openalex.org/W4387214903","https://openalex.org/W2952752702"],"abstract_inverted_index":{"Natural":[0],"conversations":[1],"are":[2,28],"spontaneous":[3],"exchanges":[4],"involving":[5],"two":[6],"or":[7],"more":[8],"people":[9],"speaking":[10],"in":[11,109,115],"an":[12,113],"intermittent":[13,127],"manner.":[14],"Therefore":[15],"one":[16],"expects":[17],"such":[18],"conversation":[19],"to":[20,42,86],"have":[21,68],"intervals":[22],"where":[23,64],"some":[24],"of":[25,50,72,120],"the":[26,39,47,51,65,73,81,88,97,101,118,121],"speakers":[27],"silent.":[29],"Yet,":[30],"most":[31],"(multichannel)":[32],"audio":[33],"source":[34],"separation":[35],"(MASS)":[36],"methods":[37],"consider":[38],"sound":[40,89],"sources":[41,66,74,90],"be":[43],"continuously":[44],"emitting":[45],"on":[46],"total":[48],"duration":[49],"processed":[52],"mixture.":[53],"In":[54],"this":[55],"paper":[56],"we":[57],"propose":[58],"a":[59,78],"probabilistic":[60],"model":[61,99,105],"for":[62,107],"MASS":[63,108],"may":[67],"pauses.":[69],"The":[70],"activity":[71],"is":[75],"modeled":[76],"as":[77],"hidden":[79],"state,":[80,83],"diarization":[82,98],"enabling":[84],"us":[85],"activate/de-activate":[87],"at":[91],"time":[92],"frame":[93],"resolution.":[94],"We":[95],"plug":[96],"within":[100],"spatial":[102],"covariance":[103],"matrix":[104],"proposed":[106],"[1],":[110],"and":[111],"obtain":[112],"improvement":[114],"performance":[116],"over":[117],"state":[119],"art":[122],"when":[123],"separating":[124],"mixtures":[125],"with":[126],"speakers.":[128]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}