{"id":"https://openalex.org/W1603689368","doi":"https://doi.org/10.21437/interspeech.2010-631","title":"Overlap detection for speaker diarization by fusing spectral and spatial features","display_name":"Overlap detection for speaker diarization by fusing spectral and spatial features","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W1603689368","doi":"https://doi.org/10.21437/interspeech.2010-631","mag":"1603689368"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-631","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2117/11288","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":true,"raw_author_name":"Martin Zelen\u00e1k","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023990637","display_name":"Carlos Segura","orcid":"https://orcid.org/0000-0002-5431-5927"},"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":"Carlos Segura","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain","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":["Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019518554"],"corresponding_institution_ids":["https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":4.1894,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.937988,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2302","last_page":"2305"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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":0.9987999796867371,"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":0.998199999332428,"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":0.9767000079154968,"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":0.9024585485458374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.753545880317688},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.631775975227356},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5301117897033691},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.48929187655448914},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47686490416526794},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4591182768344879},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.41657713055610657},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07981085777282715}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9024585485458374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.753545880317688},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.631775975227356},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5301117897033691},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.48929187655448914},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47686490416526794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4591182768344879},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.41657713055610657},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07981085777282715}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2010-631","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:recercat.cat:2072/193084","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/11288","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:recercat.cat:2072/193084","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/11288","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"A":[0],"substantial":[1],"portion":[2],"of":[3,5,23],"errors":[4],"the":[6,21],"conventional":[7],"speaker\\ndiarization":[8],"systems":[9],"on":[10,31],"meeting":[11],"data":[12],"can":[13],"be":[14],"accounted":[15],"to":[16,26,54],"overlapped\\nspeech.":[17],"This":[18],"paper":[19],"proposes":[20],"use":[22],"several":[24],"spatial\\nfeatures":[25],"improve":[27,55],"speech":[28],"overlap":[29,50,62],"detection":[30,51],"distant":[32],"channel\\nmicrophones.":[33],"These":[34],"spatial":[35],"features":[36],"are":[37],"integrated":[38],"into":[39],"a\\nspectral-based":[40],"system":[41],"by":[42],"using":[43],"principal":[44],"component":[45],"analysis\\nand":[46],"neural":[47],"networks.":[48],"Different":[49],"hypotheses\\nare":[52],"used":[53],"diarization":[56],"performance":[57],"with":[58],"both":[59],"overlap\\nexclusion":[60],"and":[61,77,81],"labeling.":[63],"In":[64],"experiments":[65],"conducted\\non":[66],"AMI":[67],"Meeting":[68],"Corpus":[69],"we":[70],"demonstrate":[71],"a":[72],"relative":[73],"DER":[74],"improvement\\nof":[75],"11.6%":[76],"14.6%":[78],"for":[79],"single-":[80],"multi-site":[82],"data,\\nrespectively.":[83]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
