{"id":"https://openalex.org/W80245499","doi":"https://doi.org/10.21437/interspeech.2012-165","title":"Speaker diarization of overlapping speech based on silence distribution in meeting recordings","display_name":"Speaker diarization of overlapping speech based on silence distribution in meeting recordings","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W80245499","doi":"https://doi.org/10.21437/interspeech.2012-165","mag":"80245499"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-165","doi":"https://doi.org/10.21437/interspeech.2012-165","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-165","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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 2012","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://infoscience.epfl.ch/bitstreams/e7078205-c6db-43b3-860c-c80b149f2e34/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065571234","display_name":"Sree Harsha Yella","orcid":null,"observed_orcids":[]},"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":"Sree Harsha Yella","raw_affiliation_strings":["IDIAP research institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061495800","display_name":"Fabio Valente","orcid":null,"observed_orcids":[]},"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":2.4533,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.89827358,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"490","last_page":"493"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9883000254631042,"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":0.9883000254631042,"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":0.008500000461935997,"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/T12031","display_name":"Speech and dialogue systems","score":0.002300000051036477,"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/speaker-diarization","display_name":"speaker diarization","score":0.9959999918937683},{"id":"https://openalex.org/keywords/overlapping-speech","display_name":"overlapping speech","score":0.9829999804496765},{"id":"https://openalex.org/keywords/overlap-detection","display_name":"overlap detection","score":0.8080000281333923},{"id":"https://openalex.org/keywords/meeting-recordings","display_name":"meeting recordings","score":0.9229999780654907},{"id":"https://openalex.org/keywords/ami-corpus","display_name":"AMI corpus","score":0.6940000057220459},{"id":"https://openalex.org/keywords/mel-frequency-cepstral-coefficients","display_name":"Mel-frequency cepstral coefficients","score":0.921999990940094},{"id":"https://openalex.org/keywords/spontaneous-conversation","display_name":"spontaneous conversation","score":0.7900000214576721}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7641624212265015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7536653280258179},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7308897972106934},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6953079700469971},{"id":"https://openalex.org/C2781115785","wikidata":"https://www.wikidata.org/wiki/Q502261","display_name":"Silence","level":2,"score":0.6516309380531311},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5406306385993958},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4811859726905823},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4418233036994934},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4219781458377838},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38007810711860657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37695974111557007},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.19511142373085022},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1437404453754425},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1373540461063385},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11547103524208069},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06753230094909668},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2012-165","doi":"https://doi.org/10.21437/interspeech.2012-165","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-165","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:192713","doi":null,"is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192713","pdf_url":"https://infoscience.epfl.ch/bitstreams/e7078205-c6db-43b3-860c-c80b149f2e34/download","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,"listed_in":[],"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"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":"pmh:oai:infoscience.tind.io:192713","doi":null,"is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/98543","pdf_url":"https://infoscience.epfl.ch/record/192713/files/Yella_INTERSPEECH_2012.pdf","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,"listed_in":[],"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"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":null,"raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:192713","doi":null,"is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192713","pdf_url":"https://infoscience.epfl.ch/bitstreams/e7078205-c6db-43b3-860c-c80b149f2e34/download","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,"listed_in":[],"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"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":[],"sustainable_development_goals_aurora":[{"score":0.8199999928474426,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W80245499.pdf","grobid_xml":"https://content.openalex.org/works/W80245499.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W79817894","https://openalex.org/W191366985","https://openalex.org/W262275730","https://openalex.org/W1485783873","https://openalex.org/W1558276682","https://openalex.org/W1603689368","https://openalex.org/W1988540447","https://openalex.org/W2081074144","https://openalex.org/W2097583714","https://openalex.org/W2098726438","https://openalex.org/W2105890227","https://openalex.org/W2106103082","https://openalex.org/W2406713305"],"related_works":["https://openalex.org/W7100401918","https://openalex.org/W2101702585","https://openalex.org/W2114970513","https://openalex.org/W1836484791","https://openalex.org/W43416829","https://openalex.org/W2169264834","https://openalex.org/W2097583714","https://openalex.org/W1603689368","https://openalex.org/W2187317003","https://openalex.org/W2103348173"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,152,175],"of":[2,18,38,66,76,93,95,106,131,139,162,171],"meetings":[3],"can":[4],"be":[5],"significantly":[6],"improved":[7],"by":[8,60,179],"overlap":[9,28,41,96,124,150],"handling.":[10],"Several":[11],"previous":[12],"works":[13],"have":[14],"explored":[15],"the":[16,61,74,86,91,104,134,137,184],"use":[17,138],"different":[19],"features":[20,120],"such":[21,146],"as":[22],"spectral,":[23],"spatial":[24],"and":[25,40,141,164],"energy":[26],"for":[27,148],"detection.":[29],"This":[30],"paper":[31,135],"proposes":[32],"a":[33,44,98],"method":[34],"to":[35,103,158,167,183],"estimate":[36],"probabilities":[37],"speech":[39],"classes":[42],"at":[43],"segment":[45,99],"level":[46],"which":[47],"are":[48,127],"later":[49],"incorporated":[50],"into":[51],"an":[52,122],"HMM/GMM":[53,123],"baseline":[54,185],"system.":[55],"The":[56],"estimation":[57],"is":[58,78,100,113,177],"motivated":[59],"observation":[62],"that":[63,90],"significant":[64],"portion":[65],"overlaps":[67],"in":[68,97,108,121,129,151,160,169],"spontaneous":[69],"conversations":[70],"take":[71],"place":[72],"where":[73],"amount":[75,105],"silence":[77,107],"less,":[79],"e.g.,":[80],"during":[81],"speaker":[82,174],"changes.":[83],"Experiments":[84],"on":[85,145,188],"AMI":[87],"corpus":[88],"reveal":[89],"probability":[92],"occurrence":[94],"inversely":[101],"proportional":[102],"it.":[109],"Whenever":[110],"this":[111],"information":[112,117],"combined":[114],"with":[115],"acoustic":[116,189],"from":[118,156,165],"MFCC":[119],"detector,":[125],"improvements":[126,155],"verified":[128],"terms":[130],"F-measure.":[132],"Furthermore":[133],"investigates":[136],"exclusion":[140,163],"labelling":[142],"strategies":[143],"based":[144,186],"detector":[147],"handling":[149],"reporting":[153],"F-measure":[154],"0.29":[157],"0.43":[159],"case":[161,170],"0.15":[166],"0.22":[168],"labelling.":[172],"Consequently":[173],"error":[176],"reduced":[178],"8%":[180],"relative":[181],"compared":[182],"solely":[187],"information.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3}],"updated_date":"2026-10-20T09:52:01.089006","created_date":"2016-06-24T00:00:00"}
