{"id":"https://openalex.org/W2157287565","doi":"https://doi.org/10.1109/icassp.2010.5495086","title":"Multistream speaker diarization beyond two acoustic feature streams","display_name":"Multistream speaker diarization beyond two acoustic feature streams","publication_year":2010,"publication_date":"2010-03-01","ids":{"openalex":"https://openalex.org/W2157287565","doi":"https://doi.org/10.1109/icassp.2010.5495086","mag":"2157287565"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/146336","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080162701","display_name":"Deepu Vijayasenan","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Deepu Vijayasenan","raw_affiliation_strings":["Ecole Polytechnique Federale de Lausanne, Lausanne, Switzerland","Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique Federale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061495800","display_name":"Fabio Valente","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Fabio Valente","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108187466","display_name":"Herv\u00e9 Bourlard","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Herve Bourlard","raw_affiliation_strings":["Ecole Polytechnique Federale de Lausanne, Lausanne, Switzerland","Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique Federale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4950","last_page":"4953"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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":0.9958999752998352,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8388611078262329},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7878897786140442},{"id":"https://openalex.org/keywords/multilateration","display_name":"Multilateration","score":0.7633902430534363},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.708171010017395},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6912016868591309},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6585472822189331},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6446509957313538},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6211576461791992},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.49507084488868713},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.44706422090530396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4189334511756897},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4069310426712036},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.07579302787780762}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8388611078262329},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878897786140442},{"id":"https://openalex.org/C104037064","wikidata":"https://www.wikidata.org/wiki/Q1640884","display_name":"Multilateration","level":3,"score":0.7633902430534363},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.708171010017395},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6912016868591309},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6585472822189331},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6446509957313538},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6211576461791992},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.49507084488868713},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.44706422090530396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4189334511756897},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4069310426712036},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.07579302787780762},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2010.5495086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:146336","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146336","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:146336","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146336","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320915","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1539780439","https://openalex.org/W1556474518","https://openalex.org/W1558086160","https://openalex.org/W1686946872","https://openalex.org/W1745746739","https://openalex.org/W2098726438","https://openalex.org/W2103723258","https://openalex.org/W2111677269","https://openalex.org/W2113932204","https://openalex.org/W2152483743","https://openalex.org/W2164512637","https://openalex.org/W2979454998","https://openalex.org/W6633534837","https://openalex.org/W6637108112","https://openalex.org/W6637485440"],"related_works":["https://openalex.org/W1963976507","https://openalex.org/W2206035908","https://openalex.org/W3119288895","https://openalex.org/W2185075503","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W4229940372"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,90],"for":[2],"meetings":[3],"data":[4],"are":[5,21,35,84],"recently":[6],"converging":[7],"towards":[8],"multistream":[9],"systems.":[10,43],"The":[11],"most":[12],"common":[13],"complementary":[14],"features":[15,29],"used":[16],"in":[17,103],"combination":[18,50,96],"with":[19,56,108],"MFCC":[20],"Time":[22],"Delay":[23],"of":[24,41,51,67,79,97],"Arrival":[25],"(TDOA).":[26],"Also":[27],"other":[28,52,132],"have":[30],"been":[31],"proposed":[32],"although,":[33],"there":[34],"no":[36],"reported":[37],"improvements":[38],"on":[39,75,86],"top":[40],"MFCC+TDOA":[42,112,129],"In":[44],"this":[45,120],"work":[46],"we":[47],"investigate":[48],"the":[49,65,80,95,111,116,122,128],"feature":[53,100,113,133],"sets":[54],"along":[55],"MFCC+TDOA.":[57],"We":[58],"discuss":[59],"issues":[60],"and":[61],"problems":[62],"related":[63],"to":[64,110,126],"weighting":[66],"four":[68,98],"different":[69],"streams":[70,101],"proposing":[71],"a":[72,76,104],"solution":[73],"based":[74],"smoothed":[77],"version":[78],"speaker":[81],"error.":[82],"Experiments":[83],"presented":[85],"NIST":[87],"RT06":[88],"meeting":[89],"evaluation.":[91],"Results":[92],"reveal":[93],"that":[94],"acoustic":[99],"results":[102],"30%":[105],"relative":[106],"improvement":[107],"respect":[109],"combination.":[114],"To":[115],"authors'":[117],"best":[118],"knowledge,":[119],"is":[121],"first":[123],"successful":[124],"attempt":[125],"improve":[127],"baseline":[130],"including":[131],"streams.":[134]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
