{"id":"https://openalex.org/W184144068","doi":"https://doi.org/10.21437/interspeech.2009-275","title":"Entropy based overlapped speech detection as a pre-processing stage for speaker diarization","display_name":"Entropy based overlapped speech detection as a pre-processing stage for speaker diarization","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W184144068","doi":"https://doi.org/10.21437/interspeech.2009-275","mag":"184144068"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-275","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110494410","display_name":"Oshry Ben-Harush","orcid":null},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Oshry Ben-Harush","raw_affiliation_strings":["Ben Gurion University of the Negev"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ben Gurion University of the Negev","institution_ids":["https://openalex.org/I124227911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002668439","display_name":"Itshak Lapidot","orcid":"https://orcid.org/0000-0003-1066-3441"},"institutions":[{"id":"https://openalex.org/I3129975082","display_name":"Sami Shamoon College of Engineering","ror":"https://ror.org/011aa4g29","country_code":"IL","type":"education","lineage":["https://openalex.org/I3129975082"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Itshak Lapidot","raw_affiliation_strings":["Sami-Shamoon College of Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sami-Shamoon College of Engineering","institution_ids":["https://openalex.org/I3129975082"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014705705","display_name":"Hugo Guterman","orcid":"https://orcid.org/0000-0002-3803-9862"},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Hugo Guterman","raw_affiliation_strings":["Ben Gurion University of the Negev"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ben Gurion University of the Negev","institution_ids":["https://openalex.org/I124227911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9679,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.68508287,"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":"916","last_page":"919"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9979000091552734,"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/T11309","display_name":"Music and Audio Processing","score":0.9927999973297119,"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":0.8285179734230042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7891849279403687},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7148115634918213},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6212126612663269},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5584661960601807},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5478506088256836},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5388808250427246},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5164682865142822},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4842102527618408},{"id":"https://openalex.org/keywords/constant-false-alarm-rate","display_name":"Constant false alarm rate","score":0.4803375005722046},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4700454771518707},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4659000337123871},{"id":"https://openalex.org/keywords/false-alarm","display_name":"False alarm","score":0.45739755034446716},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.4412570297718048},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41878557205200195},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4085528254508972}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8285179734230042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7891849279403687},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7148115634918213},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6212126612663269},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5584661960601807},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5478506088256836},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5388808250427246},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5164682865142822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4842102527618408},{"id":"https://openalex.org/C77052588","wikidata":"https://www.wikidata.org/wiki/Q644307","display_name":"Constant false alarm rate","level":2,"score":0.4803375005722046},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4700454771518707},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4659000337123871},{"id":"https://openalex.org/C2776836416","wikidata":"https://www.wikidata.org/wiki/Q1364844","display_name":"False alarm","level":2,"score":0.45739755034446716},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.4412570297718048},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41878557205200195},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4085528254508972},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2009-275","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W30751557","https://openalex.org/W43416829","https://openalex.org/W1558276682","https://openalex.org/W1663973292","https://openalex.org/W2049633694","https://openalex.org/W2115809627","https://openalex.org/W2136880172","https://openalex.org/W2159591770","https://openalex.org/W2169264834"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W1521049138","https://openalex.org/W2125642021","https://openalex.org/W2144208207","https://openalex.org/W2099333848"],"abstract_inverted_index":{"One":[0],"inherent":[1],"deficiency":[2],"of":[3,17,42,62,113,123],"most":[4],"diarization":[5],"systems":[6],"is":[7,66,109],"their":[8],"inability":[9],"to":[10],"handle":[11],"co-channel":[12],"or":[13,102],"overlapped":[14,57,63,128],"speech.":[15],"Most":[16],"the":[18,43,47,88,92,114,124,131],"suggested":[19,115],"algorithms":[20,78],"perform":[21],"under":[22],"singular":[23],"conditions,":[24],"require":[25],"high":[26],"computational":[27],"complexity":[28],"in":[29,46],"both":[30],"time":[31,48],"and":[32],"frequency":[33],"domains.":[34],"In":[35],"this":[36,86],"study,":[37],"frame":[38],"based":[39],"entropy":[40],"analysis":[41],"audio":[44],"data":[45],"domain":[49],"serves":[50],"as":[51,127],"a":[52,96,136],"single":[53],"feature":[54],"for":[55,94,99,111],"an":[56],"speech":[58,64,129],"detection":[59],"algorithm.":[60,116],"Identification":[61],"segments":[65],"performed":[67],"using":[68],"Gaussian":[69],"Mixture":[70],"Modeling":[71],"(GMM)":[72],"along":[73],"with":[74],"well":[75],"known":[76],"classification":[77],"applied":[79],"on":[80],"two":[81],"speaker":[82],"conversations.":[83],"By":[84],"employing":[85],"methodology,":[87],"proposed":[89,118],"method":[90,119],"eliminates":[91],"need":[93],"setting":[95],"hard":[97],"threshold":[98],"each":[100],"conversation":[101],"database.":[103],"LDC":[104],"CALLHOME":[105],"American":[106],"English":[107],"corpus":[108],"used":[110],"evaluation":[112],"The":[117],"successfully":[120],"detects":[121],"63.2%":[122],"frames":[125],"labeled":[126],"by":[130],"manual":[132],"segmentation,":[133],"while":[134],"keeping":[135],"5.4%":[137],"false-alarm":[138],"rate.":[139]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}