{"id":"https://openalex.org/W2127936745","doi":"https://doi.org/10.1109/icme.2003.1220941","title":"A fusion study in speech / music classification","display_name":"A fusion study in speech / music classification","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2127936745","doi":"https://doi.org/10.1109/icme.2003.1220941","mag":"2127936745"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2003.1220941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1220941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","raw_type":"proceedings-article"},"type":"preprint","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/A5018248112","display_name":"Julien Pinquier","orcid":"https://orcid.org/0000-0003-1556-1284"},"institutions":[{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405258862"]},{"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"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"J. Pinquier","raw_affiliation_strings":["Institut de Recherche en Informatique de Toulouse, UMR 5505 CNRS INP UPS, Toulouse, France","Inst. de Recherche en Informatique de Toulouse, CNRS, Toulouse, France"],"affiliations":[{"raw_affiliation_string":"Institut de Recherche en Informatique de Toulouse, UMR 5505 CNRS INP UPS, Toulouse, France","institution_ids":["https://openalex.org/I4210119061","https://openalex.org/I134560555","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Inst. de Recherche en Informatique de Toulouse, CNRS, Toulouse, France","institution_ids":["https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031772238","display_name":"Jean-Luc Rouas","orcid":"https://orcid.org/0000-0003-1933-0504"},"institutions":[{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555","https://openalex.org/I4405258862"]},{"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/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405258862"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"J.-L. Rouas","raw_affiliation_strings":["Institut de Recherche en Informatique de Toulouse, UMR 5505 CNRS INP UPS, Toulouse, France","Inst. de Recherche en Informatique de Toulouse, CNRS, Toulouse, France"],"affiliations":[{"raw_affiliation_string":"Institut de Recherche en Informatique de Toulouse, UMR 5505 CNRS INP UPS, Toulouse, France","institution_ids":["https://openalex.org/I4210119061","https://openalex.org/I134560555","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Inst. de Recherche en Informatique de Toulouse, CNRS, Toulouse, France","institution_ids":["https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040937351","display_name":"R\u00e9gine Andre-Obrecht","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405258862"]},{"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/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555","https://openalex.org/I4405258862"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"R. Andre-Obrecht","raw_affiliation_strings":["Institut de Recherche en Informatique de Toulouse, UMR 5505 CNRS INP UPS, Toulouse, France","Inst. de Recherche en Informatique de Toulouse, CNRS, Toulouse, France"],"affiliations":[{"raw_affiliation_string":"Institut de Recherche en Informatique de Toulouse, UMR 5505 CNRS INP UPS, Toulouse, France","institution_ids":["https://openalex.org/I4210119061","https://openalex.org/I134560555","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Inst. de Recherche en Informatique de Toulouse, CNRS, Toulouse, France","institution_ids":["https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018248112"],"corresponding_institution_ids":["https://openalex.org/I134560555","https://openalex.org/I4210119061","https://openalex.org/I1294671590"],"apc_list":null,"apc_paid":null,"fwci":2.02069376,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.87808534,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"36","issue":null,"first_page":"I","last_page":"409"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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":0.9969000220298767,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.715046763420105},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7113876342773438},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6831355094909668},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.67453533411026},{"id":"https://openalex.org/keywords/hertz","display_name":"Hertz","score":0.4903733730316162},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4623635411262512},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45457902550697327},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4366445541381836},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4245983958244324},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.41275596618652344},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4101964235305786},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3897114396095276},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07875189185142517},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.07329142093658447}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.715046763420105},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7113876342773438},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6831355094909668},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.67453533411026},{"id":"https://openalex.org/C2778447024","wikidata":"https://www.wikidata.org/wiki/Q39369","display_name":"Hertz","level":2,"score":0.4903733730316162},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4623635411262512},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45457902550697327},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4366445541381836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4245983958244324},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.41275596618652344},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4101964235305786},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3897114396095276},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07875189185142517},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.07329142093658447},{"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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2003.1220941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1220941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322892","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W122555466","https://openalex.org/W175761898","https://openalex.org/W176670434","https://openalex.org/W2031204895","https://openalex.org/W2049633694","https://openalex.org/W2054392851","https://openalex.org/W2106055371","https://openalex.org/W2106596127","https://openalex.org/W2112446559","https://openalex.org/W2115722710","https://openalex.org/W2124864596","https://openalex.org/W2128838222","https://openalex.org/W2460622420","https://openalex.org/W3129711340","https://openalex.org/W4285719527","https://openalex.org/W6607111733","https://openalex.org/W6607180710","https://openalex.org/W7048738093"],"related_works":["https://openalex.org/W2109901608","https://openalex.org/W1965525420","https://openalex.org/W2352602575","https://openalex.org/W2391318805","https://openalex.org/W1993000112","https://openalex.org/W2352990627","https://openalex.org/W2530091966","https://openalex.org/W165367075","https://openalex.org/W92542728","https://openalex.org/W3088890575"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,15],"present":[4],"and":[5,50,81,83,92,108,121],"merge":[6],"two":[7,72,78],"speech":[8,90,113],"/":[9,114],"music":[10,96,115],"classification":[11,65],"approaches":[12],"of":[13,52,70,87,101],"that":[14],"have":[16],"developed.":[17],"The":[18,36],"first":[19],"one":[20,38,99],"is":[21,32,39,67,75],"a":[22,28,68],"differentiated":[23],"modeling":[24],"approach":[25],"based":[26,40],"on":[27,41],"spectral":[29,106],"analysis,":[30],"which":[31],"implemented":[33],"with":[34,57,98],"GMM.":[35],"other":[37],"three":[42],"original":[43],"features:":[44],"entropy":[45],"modulation,":[46],"stationary":[47],"segment":[48],"duration":[49],"number":[51],"segments.":[53],"They":[54],"are":[55],"merged":[56],"the":[58,71,105],"classical":[59],"4":[60],"Hertz":[61],"modulation":[62],"energy.":[63],"Our":[64],"system":[66],"fusion":[69],"approaches.":[73],"It":[74],"divided":[76],"in":[77,112],"classifications":[79],"(speech/non-speech":[80],"music/non-music)":[82],"provides":[84],"94":[85],"%":[86,94],"accuracy":[88],"for":[89,95],"detection":[91],"90":[93],"detection,":[97],"second":[100],"input":[102],"signal.":[103],"Beside":[104],"information":[107],"GMM,":[109],"classically":[110],"used":[111],"discrimination,":[116],"simple":[117],"parameters":[118],"bring":[119],"complementary":[120],"efficient":[122],"information.":[123]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
