{"id":"https://openalex.org/W2021300257","doi":"https://doi.org/10.1109/icassp.2010.5495102","title":"An adaptive initialization method for speaker Diarization based on prosodic features","display_name":"An adaptive initialization method for speaker Diarization based on prosodic features","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2021300257","doi":"https://doi.org/10.1109/icassp.2010.5495102","mag":"2021300257"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495102","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495102","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://infoscience.epfl.ch/record/146430/files/Imseng_Idiap-RR-02-2010.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037750159","display_name":"David Imseng","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"David Imseng","raw_affiliation_strings":["Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Switzerland","Idiap Research Institute, Switzerland"],"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Idiap Research Institute, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062323483","display_name":"Gerald Friedland","orcid":"https://orcid.org/0000-0002-9400-6539"},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerald Friedland","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5037750159"],"corresponding_institution_ids":["https://openalex.org/I5124864","https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":2.7929,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90936779,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"4625 2008","issue":null,"first_page":"4946","last_page":"4949"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9918000102043152,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9854000210762024,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8343755006790161},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.8155874013900757},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.7136592864990234},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6686277985572815},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44715356826782227},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.44212624430656433}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8343755006790161},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8155874013900757},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7136592864990234},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6686277985572815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44715356826782227},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.44212624430656433},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2010.5495102","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495102","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.tind.io:146430","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146430","pdf_url":"https://infoscience.epfl.ch/record/146430/files/Imseng_Idiap-RR-02-2010.pdf","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/146430","raw_type":"Text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.375.7319","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.375.7319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://publications.idiap.ch/downloads/papers/2010/Imseng_ICASSP_2010.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:146062","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146062","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:146430","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146430","pdf_url":"https://infoscience.epfl.ch/record/146430/files/Imseng_Idiap-RR-02-2010.pdf","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/146430","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2021300257.pdf"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W71947379","https://openalex.org/W184241528","https://openalex.org/W1524832141","https://openalex.org/W1556474518","https://openalex.org/W1556857061","https://openalex.org/W2126432406","https://openalex.org/W2156255174","https://openalex.org/W2164512637","https://openalex.org/W2338994564","https://openalex.org/W6602894216","https://openalex.org/W6659344013","https://openalex.org/W7005290334"],"related_works":["https://openalex.org/W184241528","https://openalex.org/W2206035908","https://openalex.org/W4297807400","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":{"The":[0,41,72],"following":[1],"article":[2],"presents":[3],"a":[4,45,58,127],"novel,":[5],"adaptive":[6],"initialization":[7,42,74,104],"scheme":[8],"that":[9,21,110],"can":[10],"be":[11],"applied":[12],"to":[13,135],"most":[14],"state-of-the-art":[15],"Speaker":[16],"Diarization":[17,128],"algorithms,":[18],"i.e.":[19],"algorithms":[20],"use":[22],"agglomerative":[23],"hierarchical":[24],"clustering":[25],"with":[26],"Bayesian":[27],"Information":[28],"Criterion":[29],"(BIC)":[30],"and":[31,57,61,87,93,117,124],"Gaussian":[32],"Mixture":[33],"Models":[34],"(GMMs)":[35],"of":[36,47,63,133],"frame-based":[37],"cepstral":[38],"features":[39],"(MFCCs).":[40],"method":[43,56,67,75,82,99],"is":[44,88],"combination":[46],"the":[48,81,98,114],"recently":[49],"proposed":[50],"\u201cadaptive":[51],"seconds":[52],"per":[53],"Gaussian\u201d":[54],"(ASPG)":[55],"new":[59],"pre-clustering":[60],"number":[62],"initial":[64],"clusters":[65],"estimation":[66],"based":[68],"on":[69,106],"prosodic":[70],"features.":[71],"presented":[73,112],"has":[76],"two":[77],"important":[78],"advantages.":[79],"First,":[80],"requires":[83],"no":[84],"manual":[85],"tuning":[86],"robust":[89],"against":[90],"file":[91],"length":[92],"speaker":[94],"count":[95],"variations.":[96],"Second,":[97],"outperforms":[100],"our":[101],"previously":[102],"used":[103],"methods":[105],"all":[107],"benchmark":[108],"files":[109],"were":[111],"in":[113,126],"2006,":[115],"2007,":[116],"2009":[118],"NIST":[119],"Rich":[120],"Transcription":[121],"(RT)":[122],"evaluations":[123],"results":[125],"Error":[129],"Rate":[130],"(DER)":[131],"improvement":[132],"up":[134],"67%":[136],"(relative).":[137]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}