{"id":"https://openalex.org/W2111339787","doi":"https://doi.org/10.1109/icassp.2002.5743713","title":"Robust HMM-based speech/music segmentation","display_name":"Robust HMM-based speech/music segmentation","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2111339787","doi":"https://doi.org/10.1109/icassp.2002.5743713","mag":"2111339787"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743713","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743713","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"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/bitstreams/f0d7e6f2-3d2d-45f9-9d0e-6d70c1d5abde/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063781689","display_name":"Jitendra Ajmera","orcid":null},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]},{"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":"Jitendra Ajmera","raw_affiliation_strings":["Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland","Daile Molle Institute for Perceptual Artificial Intelligence (IDIAP), P. O. Box 592, CH-1920 Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]},{"raw_affiliation_string":"Daile Molle Institute for Perceptual Artificial Intelligence (IDIAP), P. O. Box 592, CH-1920 Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072372659","display_name":"Iain McCowan","orcid":null},"institutions":[{"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"]},{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Iain A. McCowan","raw_affiliation_strings":["Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland","Daile Molle Institute for Perceptual Artificial Intelligence (IDIAP), P. O. Box 592, CH-1920 Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]},{"raw_affiliation_string":"Daile Molle Institute for Perceptual Artificial Intelligence (IDIAP), P. O. Box 592, CH-1920 Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108187466","display_name":"Herv\u00e9 Bourlard","orcid":null},"institutions":[{"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"]},{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Herve Bourlard","raw_affiliation_strings":["Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland","Daile Molle Institute for Perceptual Artificial Intelligence (IDIAP), P. O. Box 592, CH-1920 Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]},{"raw_affiliation_string":"Daile Molle Institute for Perceptual Artificial Intelligence (IDIAP), P. O. Box 592, CH-1920 Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063781689"],"corresponding_institution_ids":["https://openalex.org/I2614128279","https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":5.6091,"has_fulltext":true,"cited_by_count":44,"citation_normalized_percentile":{"value":0.97091531,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"I","last_page":"297"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8666119575500488},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7585691213607788},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7547507286071777},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6402113437652588},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5421519875526428},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.515586793422699},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.4701005816459656},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.45004141330718994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4264281988143921},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4236014485359192},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.4205498695373535},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3765206038951874},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12184494733810425}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8666119575500488},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7585691213607788},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7547507286071777},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6402113437652588},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5421519875526428},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.515586793422699},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.4701005816459656},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.45004141330718994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4264281988143921},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4236014485359192},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4205498695373535},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3765206038951874},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12184494733810425},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2002.5743713","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743713","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.tind.io:82847","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/82847","pdf_url":"https://infoscience.epfl.ch/bitstreams/f0d7e6f2-3d2d-45f9-9d0e-6d70c1d5abde/download","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":"","raw_type":"conference proceedings"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.187.1381","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.187.1381","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/reports/2001/ajmera2002icassp.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:82734","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/82734","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:82847","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/82847","pdf_url":"https://infoscience.epfl.ch/bitstreams/f0d7e6f2-3d2d-45f9-9d0e-6d70c1d5abde/download","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":"","raw_type":"conference proceedings"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5799999833106995}],"awards":[{"id":"https://openalex.org/G6110739615","display_name":"AudioSkim: Automatic segmentation of large audio and multimedia documents","funder_award_id":"65067","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2111339787.pdf","grobid_xml":"https://content.openalex.org/works/W2111339787.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W1482605500","https://openalex.org/W2106055371","https://openalex.org/W2106339924","https://openalex.org/W2124864596","https://openalex.org/W2128838222","https://openalex.org/W4402491236","https://openalex.org/W6628911050"],"related_works":["https://openalex.org/W2136652457","https://openalex.org/W2169849734","https://openalex.org/W2116722627","https://openalex.org/W2129150969","https://openalex.org/W2236912844","https://openalex.org/W1975869217","https://openalex.org/W2401728283","https://openalex.org/W2383829109","https://openalex.org/W2379938888","https://openalex.org/W2386035178"],"abstract_inverted_index":{"In":[0,24],"this":[1],"paper":[2],"we":[3],"present":[4],"a":[5,44,64,90,97,135],"new":[6],"approach":[7,26],"towards":[8],"high":[9],"performance":[10],"speech/music":[11],"segmentation":[12],"on":[13,37],"realistic":[14],"tasks":[15],"related":[16],"to":[17],"the":[18,25,29,48,52,81,86,125,128],"automatic":[19],"transcription":[20],"of":[21,50,80,99,110,127],"broadcast":[22],"news.":[23],"presented":[27],"here,":[28],"local":[30],"probability":[31],"density":[32],"function":[33],"(PDF)":[34],"estimators":[35],"trained":[36,84],"clean":[38],"microphone":[39],"speech":[40,100,111],"are":[41,83],"used":[42],"as":[43,104,106],"channel":[45],"model":[46,72],"at":[47],"output":[49],"which":[51,130],"entropy":[53],"and":[54,59,67,68,101,112],"\u201cdynamism\u201d":[55],"will":[56,123],"be":[57],"measured":[58],"integrated":[60],"over":[61],"time":[62],"through":[63],"2-state":[65],"(speech":[66],"non-speech)":[69],"hidden":[70],"Markov":[71],"(HMM)":[73],"with":[74],"minimum":[75],"duration":[76],"constraints.":[77],"The":[78],"parameters":[79],"HMM":[82],"using":[85],"EM":[87],"algorithm":[88],"in":[89,131],"completely":[91],"unsupervised":[92],"manner.":[93],"Different":[94],"experiments,":[95],"including":[96],"variety":[98],"music":[102,113],"styles,":[103],"well":[105],"different":[107],"segment":[108],"durations":[109],"signals":[114],"(real":[115],"data":[116],"distribution,":[117],"mostly":[118,121],"speech,":[119],"or":[120],"music),":[122],"illustrate":[124],"robustness":[126],"approach,":[129],"each":[132],"case":[133],"achieves":[134],"frame-level":[136],"accuracy":[137],"greater":[138],"than":[139],"94%.":[140]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"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":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}