{"id":"https://openalex.org/W2482731677","doi":"https://doi.org/10.21437/odyssey.2016-58","title":"Short- and Long-Term Speech Features for Hybrid HMM-i-Vector based Speaker Diarization System","display_name":"Short- and Long-Term Speech Features for Hybrid HMM-i-Vector based Speaker Diarization System","publication_year":2016,"publication_date":"2016-06-21","ids":{"openalex":"https://openalex.org/W2482731677","doi":"https://doi.org/10.21437/odyssey.2016-58","mag":"2482731677"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2016-58","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2016-58","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2016)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/2117/101681","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080459470","display_name":"Abraham Woubie Zewoudie","orcid":"https://orcid.org/0000-0002-5666-1831"},"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":"Abraham Woubie Zewoudie","raw_affiliation_strings":["TALP Research Center, Department of Signal Theory and Communications, Universitat Politecnica de Catalunya, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TALP Research Center, Department of Signal Theory and Communications, Universitat Politecnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071561412","display_name":"Jordi Luque","orcid":"https://orcid.org/0000-0002-4507-4930"},"institutions":[{"id":"https://openalex.org/I4210097190","display_name":"Telef\u00f3nica (Spain)","ror":"https://ror.org/012f7tj07","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210097190"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jordi Luque","raw_affiliation_strings":["Telefonica Research, Edificio Telefonica-Diagonal, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Telefonica Research, Edificio Telefonica-Diagonal, Barcelona, Spain","institution_ids":["https://openalex.org/I4210097190"]}]},{"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":["TALP Research Center, Department of Signal Theory and Communications, Universitat Politecnica de Catalunya, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TALP Research Center, Department of Signal Theory and Communications, Universitat Politecnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0912,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.92972576,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"400","last_page":"406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9958999752998352,"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/T10860","display_name":"Speech and Audio Processing","score":0.9943000078201294,"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":0.814702570438385},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7464503049850464},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7267088294029236},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6533867716789246},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5926691293716431},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5675591230392456},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.5515161752700806},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.5346765518188477},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.531866192817688},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5056023597717285},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.47915714979171753},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4761119782924652},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45971325039863586},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.42501574754714966},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4139007031917572},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.41206637024879456},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2929074764251709}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.814702570438385},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7464503049850464},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7267088294029236},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6533867716789246},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5926691293716431},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5675591230392456},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.5515161752700806},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.5346765518188477},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.531866192817688},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5056023597717285},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.47915714979171753},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4761119782924652},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45971325039863586},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.42501574754714966},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4139007031917572},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.41206637024879456},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2929074764251709},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/odyssey.2016-58","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2016-58","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2016)","raw_type":"proceedings-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/101681","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/101681","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:www.recercat.cat:2072/281049","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/101681","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:upcommons.upc.edu:2117/101681","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/101681","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2888922458","display_name":null,"funder_award_id":"TEC2015-69266-P","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"},{"id":"https://openalex.org/G6095252267","display_name":"BIg Speech data analytics for cONtact centres","funder_award_id":"645323","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7963379398","display_name":"Annotation collaborative de documents multi-modaux, multi-lingues et multi-m\u00e9dia","funder_award_id":"ANR-12-CHRI-0006","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320321505","display_name":"Generalitat de Catalunya","ror":"https://ror.org/01bg62x04"},{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W44948719","https://openalex.org/W191366985","https://openalex.org/W579783719","https://openalex.org/W1989674379","https://openalex.org/W2081074144","https://openalex.org/W2089542572","https://openalex.org/W2102518334","https://openalex.org/W2115599677","https://openalex.org/W2115861008","https://openalex.org/W2128915671","https://openalex.org/W2150769028","https://openalex.org/W2151534428","https://openalex.org/W2153410846","https://openalex.org/W2156255174","https://openalex.org/W2164512637","https://openalex.org/W2240726287","https://openalex.org/W2289985966","https://openalex.org/W2290266542","https://openalex.org/W2399762392","https://openalex.org/W2400584454","https://openalex.org/W2981666567"],"related_works":["https://openalex.org/W1963976507","https://openalex.org/W2206035908","https://openalex.org/W3119288895","https://openalex.org/W2185075503","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W4229940372"],"abstract_inverted_index":{"i-vectors":[0,41,104],"have":[1],"been":[2],"successfully":[3],"applied":[4],"over":[5],"the":[6,18,24,61,65,68,76,98,134,140,149,157],"last":[7],"years":[8],"in":[9,168],"speaker":[10,27,45,122,189],"recognition":[11],"tasks.":[12],"This":[13],"work":[14,184],"aims":[15],"at":[16],"assessing":[17],"suitability":[19,141],"of":[20,26,40,67,82,101,133,142,146,159,170],"i-vector":[21,63,150,160,196,201],"modeling":[22],"within":[23,148],"frame":[25],"diarization":[28,171],"task.":[29],"In":[30,88],"such":[31],"context,":[32],"a":[33,80,110,165,187,199],"weighted":[34,107],"cosine-distance":[35,99],"between":[36],"two":[37,57,103,129],"different":[38,58,130],"sets":[39,132],"is":[42,118],"proposed":[43],"for":[44],"clustering.":[46],"Speech":[47],"clusters":[48],"generated":[49],"by":[50,56,192],"Viterbi":[51],"segmentation":[52],"are":[53,105],"first":[54,62],"modeled":[55],"i-vectors.":[59],"Whilst":[60],"represents":[64],"distribution":[66],"commonly":[69],"used":[70,120],"short-term":[71,194],"Mel":[72],"Frequency":[73],"Cepstral":[74],"Coefficients,":[75],"second":[77,200],"one":[78],"depicts":[79],"selection":[81],"voice":[83,204],"quality":[84,205],"and":[85,94,206],"prosodic":[86],"features.":[87,210],"order":[89],"to":[90,108],"combine":[91],"both":[92,144],"short-":[93],"long-term":[95],"speech":[96,209],"statistics,":[97],"scores":[100],"those":[102,175],"linearly":[106],"obtain":[109],"unique":[111],"similarity":[112],"score.":[113],"The":[114],"final":[115],"fused":[116],"score":[117],"then":[119],"as":[121],"clustering":[123,162,197],"distance.":[124],"Our":[125,152],"experimental":[126,153],"results":[127,154],"on":[128,177],"evaluation":[131],"Augmented":[135],"Multi-party":[136],"Interaction":[137],"corpus":[138],"show":[139,155],"combining":[143],"sources":[145],"information":[147],"space.":[151],"that":[156],"use":[158],"based":[161,176,195],"technique":[163],"provide":[164],"significant":[166,188],"improvement,":[167],"terms":[169],"error":[172,190],"rate,":[173],"than":[174],"Gaussian":[178],"Mixture":[179],"Modeling":[180],"technique.":[181],"Furthermore,":[182],"this":[183],"also":[185],"reports":[186],"reduction":[191],"augmenting":[193],"with":[198],"estimated":[202],"from":[203],"prosody":[207],"related":[208]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}