{"id":"https://openalex.org/W2109240172","doi":"https://doi.org/10.1109/icassp.2009.4959921","title":"A regularized kernel-based approach to unsupervised audio segmentation","display_name":"A regularized kernel-based approach to unsupervised audio segmentation","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2109240172","doi":"https://doi.org/10.1109/icassp.2009.4959921","mag":"2109240172"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4959921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4959921","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5010613767","display_name":"Za\u00efd Harchaoui","orcid":"https://orcid.org/0000-0003-1186-1343"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Zaid Harchaoui","raw_affiliation_strings":["LTCI,CNRS LTCI, TELECOM ParisTech, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI,CNRS LTCI, TELECOM ParisTech, Paris, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210165912","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036989164","display_name":"F\u00e9licien Vallet","orcid":null},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210125774","display_name":"Institut National de l'Audiovisuel","ror":"https://ror.org/02zwkwz55","country_code":"FR","type":"other","lineage":["https://openalex.org/I4210125774"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Felicien Vallet","raw_affiliation_strings":["Institut National de l'Audiovisuel, Bry-sur-Marne, France","LTCI,CNRS LTCI, TELECOM ParisTech, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut National de l'Audiovisuel, Bry-sur-Marne, France","institution_ids":["https://openalex.org/I4210125774"]},{"raw_affiliation_string":"LTCI,CNRS LTCI, TELECOM ParisTech, Paris, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210165912","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086780984","display_name":"Alexandre Lung-Yut-Fong","orcid":null},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Alexandre Lung-Yut-Fong","raw_affiliation_strings":["LTCI,CNRS LTCI, TELECOM ParisTech, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI,CNRS LTCI, TELECOM ParisTech, Paris, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210165912","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105628617","display_name":"Olivier Capp\u00e9","orcid":null},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier Cappe","raw_affiliation_strings":["LTCI,CNRS LTCI, TELECOM ParisTech, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI,CNRS LTCI, TELECOM ParisTech, Paris, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210165912","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1665","last_page":"1668"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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":0.9969000220298767,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9289000034332275,"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/computer-science","display_name":"Computer science","score":0.6818777918815613},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6527009010314941},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6198212504386902},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.603628396987915},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5141992568969727},{"id":"https://openalex.org/keywords/radial-basis-function-kernel","display_name":"Radial basis function kernel","score":0.440307080745697},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.4362734854221344},{"id":"https://openalex.org/keywords/false-alarm","display_name":"False alarm","score":0.4217090606689453},{"id":"https://openalex.org/keywords/constant-false-alarm-rate","display_name":"Constant false alarm rate","score":0.42079344391822815},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4157543182373047},{"id":"https://openalex.org/keywords/kernel-fisher-discriminant-analysis","display_name":"Kernel Fisher discriminant analysis","score":0.4144608974456787},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.407241553068161},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.33775174617767334},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24569037556648254},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.20827719569206238}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6818777918815613},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6527009010314941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6198212504386902},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.603628396987915},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5141992568969727},{"id":"https://openalex.org/C75866337","wikidata":"https://www.wikidata.org/wiki/Q7280263","display_name":"Radial basis function kernel","level":4,"score":0.440307080745697},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.4362734854221344},{"id":"https://openalex.org/C2776836416","wikidata":"https://www.wikidata.org/wiki/Q1364844","display_name":"False alarm","level":2,"score":0.4217090606689453},{"id":"https://openalex.org/C77052588","wikidata":"https://www.wikidata.org/wiki/Q644307","display_name":"Constant false alarm rate","level":2,"score":0.42079344391822815},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4157543182373047},{"id":"https://openalex.org/C181367576","wikidata":"https://www.wikidata.org/wiki/Q6394184","display_name":"Kernel Fisher discriminant analysis","level":4,"score":0.4144608974456787},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.407241553068161},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.33775174617767334},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24569037556648254},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.20827719569206238},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2009.4959921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4959921","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.324.5024","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.324.5024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.harchaoui.eu/zaid/publications/harchaoui_vallet_lung_cappe_2009_kerseg.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1510073064","https://openalex.org/W1827418370","https://openalex.org/W2044591814","https://openalex.org/W2106055371","https://openalex.org/W2110762162","https://openalex.org/W2124623336","https://openalex.org/W2125865219","https://openalex.org/W2128838222","https://openalex.org/W2139421285","https://openalex.org/W2140095548","https://openalex.org/W2144345993","https://openalex.org/W2148477345","https://openalex.org/W2155691655","https://openalex.org/W2951907984","https://openalex.org/W6678814708","https://openalex.org/W6682973090","https://openalex.org/W6764534809"],"related_works":["https://openalex.org/W2515338903","https://openalex.org/W2610521515","https://openalex.org/W1509134351","https://openalex.org/W3033319502","https://openalex.org/W2905418897","https://openalex.org/W2015311866","https://openalex.org/W2043888321","https://openalex.org/W2108995755","https://openalex.org/W2068526999","https://openalex.org/W2114252311"],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,12,43,58,103],"regularized":[3],"kernel-based":[4,26,97],"rule":[5],"for":[6,64,71,82],"unsupervised":[7],"change":[8,27],"detection":[9],"based":[10],"on":[11],"simpler":[13],"version":[14],"of":[15],"the":[16,31,33,54,86,92],"recently":[17],"proposed":[18,34,93],"kernel":[19],"fisher":[20],"discriminant":[21],"ratio.":[22],"Compared":[23],"to":[24,39,52],"other":[25,96],"detectors":[28],"found":[29],"in":[30],"literature,":[32],"test":[35],"statistic":[36],"is":[37,62,100],"easier":[38],"compute":[40],"and":[41,81,99],"has":[42],"known":[44],"asymptotic":[45],"distribution":[46],"which":[47],"can":[48],"effectively":[49],"be":[50],"used":[51],"set":[53],"false":[55],"alarm":[56],"rate":[57],"priori.":[59],"This":[60],"technique":[61],"applied":[63],"segmenting":[65],"tracks":[66],"from":[67],"TV":[68],"shows,":[69],"both":[70],"segmentation":[72],"into":[73],"semantically":[74],"homogeneous":[75],"sections":[76],"(applause,":[77],"movie,":[78],"music,":[79],"etc.)":[80],"speaker":[83],"diarization":[84],"within":[85],"speech":[87],"sections.":[88],"On":[89],"these":[90],"tasks,":[91],"approach":[94],"outperforms":[95],"tests":[98],"competitive":[101],"with":[102],"standard":[104],"HMM-based":[105],"supervised":[106],"alternative.":[107]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}