{"id":"https://openalex.org/W196703252","doi":"https://doi.org/10.21437/interspeech.2007-736","title":"The influence of speech activity detection and overlap on speaker diarization for meeting room recordings","display_name":"The influence of speech activity detection and overlap on speaker diarization for meeting room recordings","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W196703252","doi":"https://doi.org/10.21437/interspeech.2007-736","mag":"196703252"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-736","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","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/A5018458807","display_name":"Corinne Fredouille","orcid":"https://orcid.org/0000-0002-0413-8950"},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Corinne Fredouille","raw_affiliation_strings":["University of Avignon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Avignon","institution_ids":["https://openalex.org/I198415970"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066811192","display_name":"Nicholas Evans","orcid":"https://orcid.org/0000-0002-8459-1041"},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicholas Evans","raw_affiliation_strings":["University of Avignon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Avignon","institution_ids":["https://openalex.org/I198415970"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I198415970"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2953","last_page":"2956"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9945999979972839,"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":0.9376294612884521},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.788425087928772},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7613558769226074},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7061185836791992},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6013960242271423},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5327145457267761},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5029627680778503},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.47096139192581177},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4293123185634613},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4195703864097595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2569894790649414},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.19263219833374023}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9376294612884521},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.788425087928772},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7613558769226074},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7061185836791992},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6013960242271423},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5327145457267761},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5029627680778503},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.47096139192581177},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4293123185634613},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4195703864097595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2569894790649414},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.19263219833374023},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2007-736","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W64459544","https://openalex.org/W106647055","https://openalex.org/W2052269122","https://openalex.org/W2097470427","https://openalex.org/W2124078061","https://openalex.org/W2147520277"],"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/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2022789108","https://openalex.org/W2009814707"],"abstract_inverted_index":{"Abstract":[0],"This":[1],"paper":[2,51],"addresses":[3],"the":[4,53,66,81],"problem":[5],"of":[6,12,22,49,55,83],"speaker":[7,29,37,62,122,127],"diarization":[8,63],"inthe":[9],"speci\ufb01c":[10],"context":[11],"meeting":[13,129],"room":[14],"recordings":[15],"which":[16],"of-ten":[17],"involve":[18],"a":[19,117],"high":[20],"degree":[21],"spontaneous":[23],"speech":[24,27,56,60,131],"with":[25],"largeoverlapped":[26],"segments,":[28],"noise":[30],"(laughs,":[31],"whispers,coughs,":[32],"etc.)":[33],"and":[34,69,86],"very":[35],"short":[36],"turns.":[38],"A":[39],"large":[40],"variabilityin":[41],"signal":[42],"quality":[43],"has":[44],"brought":[45],"an":[46],"additional":[47],"level":[48],"complexity.This":[50],"investigates":[52],"effects":[54],"activity":[57],"detectionand":[58],"overlapped":[59,134],"through":[61],"experimentsconducted":[64],"on":[65],"NIST":[67],"RT\u201905":[68],"RT\u201906":[70],"data":[71],"sets.":[72],"Resultsindicate":[73],"that":[74],"our":[75],"system":[76],"is":[77,115],"highly":[78],"sensitive":[79],"to":[80,103,107,112,121],"shape":[82],"theinitial":[84],"segmentation":[85],"that,":[87],"perhaps":[88],"surprisingly,":[89],"perfect":[90],"ref-erences":[91],"can":[92],"even":[93],"degrade":[94],"performance.":[95],"Finally":[96],"we":[97],"propose":[98],"adirection":[99],"for":[100],"future":[101],"research":[102],"incorporate":[104],"con\ufb01dence":[105],"valuesaccording":[106],"acoustic":[108],"attributes":[109],"in":[110],"order":[111],"unify":[113],"what":[114],"cur-rently":[116],"somewhat":[118],"disjointed":[119],"approach":[120],"diarization.":[123],"Index":[124],"Terms":[125],":":[126],"diarization,":[128],"room,":[130],"activ-ity":[132],"detection,":[133],"speech.":[135]},"counts_by_year":[{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}