{"id":"https://openalex.org/W2116922797","doi":"https://doi.org/10.1109/asru.2007.4430120","title":"Efficient combination of parametric spaces, models and metrics for speaker diarization<sup>1</sup>","display_name":"Efficient combination of parametric spaces, models and metrics for speaker diarization<sup>1</sup>","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2116922797","doi":"https://doi.org/10.1109/asru.2007.4430120","mag":"2116922797"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2007.4430120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","raw_type":"proceedings-article"},"type":"article","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/A5061939508","display_name":"Themos Stafylakis","orcid":"https://orcid.org/0000-0002-9227-3588"},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Themos Stafylakis","raw_affiliation_strings":["Institute for Language and Speech Processing, Communication and Knowledge Technologies, Athens, Greece","Inst. for Language & Speech Process., Athens"],"affiliations":[{"raw_affiliation_string":"Institute for Language and Speech Processing, Communication and Knowledge Technologies, Athens, Greece","institution_ids":["https://openalex.org/I4210098364"]},{"raw_affiliation_string":"Inst. for Language & Speech Process., Athens","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060812182","display_name":"Vassilis Katsouros","orcid":"https://orcid.org/0000-0002-4185-2344"},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Vassilis Katsouros","raw_affiliation_strings":["Institute for Language and Speech Processing, Communication and Knowledge Technologies, Athens, Greece","Inst. for Language & Speech Process., Athens"],"affiliations":[{"raw_affiliation_string":"Institute for Language and Speech Processing, Communication and Knowledge Technologies, Athens, Greece","institution_ids":["https://openalex.org/I4210098364"]},{"raw_affiliation_string":"Inst. for Language & Speech Process., Athens","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108429687","display_name":"G. Carayannis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"George Carayannis","raw_affiliation_strings":["Institute for Language and Speech Processing, Communication and Knowledge Technologies, Athens, Greece","Inst. for Language & Speech Process., Athens"],"affiliations":[{"raw_affiliation_string":"Institute for Language and Speech Processing, Communication and Knowledge Technologies, Athens, Greece","institution_ids":["https://openalex.org/I4210098364"]},{"raw_affiliation_string":"Inst. for Language & Speech Process., Athens","institution_ids":["https://openalex.org/I4210098364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061939508"],"corresponding_institution_ids":["https://openalex.org/I4210098364"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10899586,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"256","last_page":"261"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9998000264167786,"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":0.9994999766349792,"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":0.835356593132019},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6680574417114258},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5912771224975586},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5807347297668457},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5482044219970703},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5279057621955872},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5246551036834717},{"id":"https://openalex.org/keywords/multidimensional-scaling","display_name":"Multidimensional scaling","score":0.504829466342926},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48676419258117676},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4589548707008362},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4573991894721985},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4479312002658844},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.43832823634147644},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4363832473754883},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3452434539794922},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.33077746629714966},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19609710574150085},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19260740280151367},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08955013751983643}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.835356593132019},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6680574417114258},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5912771224975586},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5807347297668457},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5482044219970703},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5279057621955872},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5246551036834717},{"id":"https://openalex.org/C91682802","wikidata":"https://www.wikidata.org/wiki/Q620538","display_name":"Multidimensional scaling","level":2,"score":0.504829466342926},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48676419258117676},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4589548707008362},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4573991894721985},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4479312002658844},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.43832823634147644},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4363832473754883},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3452434539794922},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.33077746629714966},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19609710574150085},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19260740280151367},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08955013751983643},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2007.4430120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W171976167","https://openalex.org/W1524222317","https://openalex.org/W2009674825","https://openalex.org/W2041823554","https://openalex.org/W2043253481","https://openalex.org/W2051195460","https://openalex.org/W2096175520","https://openalex.org/W2102667697","https://openalex.org/W2107617395","https://openalex.org/W2110215948","https://openalex.org/W2119484097","https://openalex.org/W2160842254","https://openalex.org/W2620921085","https://openalex.org/W3022906761","https://openalex.org/W4299576595","https://openalex.org/W6631445998","https://openalex.org/W6661333666","https://openalex.org/W6674650171","https://openalex.org/W6676027155","https://openalex.org/W6738833779","https://openalex.org/W6843883754"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"In":[0],"this":[1,61],"paper":[2],"we":[3,32,63],"present":[4],"a":[5,70,76],"method":[6],"of":[7,29,78],"combining":[8],"several":[9,53],"acoustic":[10],"parametric":[11],"spaces,":[12],"statistical":[13,54],"models":[14],"and":[15,38,47,87],"distance":[16,55],"metrics":[17],"in":[18],"speaker":[19],"diarization":[20],"task.":[21],"Focusing":[22],"our":[23],"interest":[24],"on":[25,42,57],"the":[26,30,43,65,79],"post-segmentation":[27],"part":[28],"problem,":[31],"adopt":[33],"an":[34],"incremental":[35],"feature":[36],"selection":[37],"fusion":[39],"algorithm":[40,91],"based":[41],"Maximum":[44],"Entropy":[45],"Principle":[46],"Iterative":[48],"Scaling":[49],"Algorithm":[50],"that":[51],"combines":[52],"measures":[56],"speech-chunk":[58],"pairs.":[59],"By":[60],"approach,":[62],"place":[64],"merging-of-chunks":[66],"clustering":[67],"process":[68],"into":[69],"probabilistic":[71],"framework.":[72],"We":[73],"also":[74],"propose":[75],"decomposition":[77],"input":[80],"space":[81],"according":[82],"to":[83,97],"gender,":[84],"recording":[85],"conditions":[86],"chunk":[88],"lengths.":[89],"The":[90],"produced":[92],"highly":[93],"competitive":[94],"results":[95],"compared":[96],"GMM-UBM":[98],"state-of-the-art":[99],"methods.":[100]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}