{"id":"https://openalex.org/W191366985","doi":"https://doi.org/10.21437/interspeech.2011-389","title":"The detection of overlapping speech with prosodic features for speaker diarization","display_name":"The detection of overlapping speech with prosodic features for speaker diarization","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W191366985","doi":"https://doi.org/10.21437/interspeech.2011-389","mag":"191366985"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-389","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2117/14815","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019518554","display_name":"Martin Zelen\u00e1k","orcid":null},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Martin Zelen\u00e1k","raw_affiliation_strings":["Polytechnic University of Catalonia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Polytechnic University of Catalonia","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025633053","display_name":"Javier Hernando","orcid":"https://orcid.org/0000-0002-1730-8154"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Javier Hernando","raw_affiliation_strings":["Polytechnic University of Catalonia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Polytechnic University of Catalonia","institution_ids":["https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8361,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.94788802,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1041","last_page":"1044"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9986000061035156,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.8975526094436646},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.8032045364379883},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7506002187728882},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7402712106704712},{"id":"https://openalex.org/keywords/intonation","display_name":"Intonation (linguistics)","score":0.5820194482803345},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.5276581048965454},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5085989236831665},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42430180311203003},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41550230979919434},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34731853008270264},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12393364310264587},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11957520246505737},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.09342005848884583}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8975526094436646},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8032045364379883},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7506002187728882},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7402712106704712},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.5820194482803345},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.5276581048965454},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5085989236831665},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42430180311203003},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41550230979919434},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34731853008270264},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12393364310264587},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11957520246505737},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.09342005848884583},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2011-389","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},{"id":"pmh:oai:recercat.cat:2072/184693","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/14815","pdf_url":null,"source":{"id":"https://openalex.org/S4306402147","display_name":"RECERCAT (Consorci de Serveis Universitaris de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210090028","host_organization_name":"Consorci de Serveis Universitaris de Catalunya","host_organization_lineage":["https://openalex.org/I4210090028"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:recercat.cat:2072/184693","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/14815","pdf_url":null,"source":{"id":"https://openalex.org/S4306402147","display_name":"RECERCAT (Consorci de Serveis Universitaris de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210090028","host_organization_name":"Consorci de Serveis Universitaris de Catalunya","host_organization_lineage":["https://openalex.org/I4210090028"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W127975155","https://openalex.org/W168261181","https://openalex.org/W265573121","https://openalex.org/W1492025301","https://openalex.org/W1603689368","https://openalex.org/W2118748593","https://openalex.org/W2127996343","https://openalex.org/W2134584072","https://openalex.org/W2148613904","https://openalex.org/W2154053567","https://openalex.org/W2164512637","https://openalex.org/W2172070182"],"related_works":["https://openalex.org/W1965454423","https://openalex.org/W2028501571","https://openalex.org/W2052542215","https://openalex.org/W2036564641","https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321"],"abstract_inverted_index":{"Overlapping":[0],"speech":[1,93],"is":[2,65],"responsible":[3],"for":[4],"a":[5,22,29,48],"certain":[6],"amount":[7],"of":[8,24,75,104],"errors":[9],"produced":[10],"by":[11,67,94],"tandard":[12],"speaker":[13,88,97,105],"diarization":[14,89],"systems":[15],"in":[16,47,87],"meeting":[17],"environment.":[18],"We":[19,70],"are":[20,45,85],"investigating":[21],"set":[23],"prosody-based":[25],"long-term":[26],"features":[27,44,77],"as":[28],"potential":[30],"complement":[31],"to":[32,57,90,100],"our":[33],"overlap":[34,79,83],"detection\\nsystem":[35],"relying":[36],"on":[37],"short-term":[38],"spectral":[39],"parameters.":[40],"The":[41],"most":[42],"relevant":[43],"selected":[46],"two-step":[49],"process.":[50],"They\\nare":[51],"firstly":[52],"evaluated":[53],"and":[54,60,99],"sorted":[55],"according":[56],"mRMR":[58],"criterion":[59],"then":[61],"the":[62,73,102],"optimal":[63],"number":[64],"determined":[66],"iterative":[68],"wrapper\\napproach.":[69],"show":[71],"that":[72],"addition":[74],"prosodic":[76],"decreased":[78],"detection":[80],"error.":[81],"Detected":[82],"segments":[84],"used":[86],"recover":[91],"missed":[92],"assigning":[95],"multiple":[96],"labels":[98],"increase":[101],"purity":[103],"clusters.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
