{"id":"https://openalex.org/W4253642683","doi":"https://doi.org/10.1109/icassp.2003.1202283","title":"A fusion study in speech/music classification","display_name":"A fusion study in speech/music classification","publication_year":2003,"publication_date":"2003-12-22","ids":{"openalex":"https://openalex.org/W4253642683","doi":"https://doi.org/10.1109/icassp.2003.1202283"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1202283","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1202283","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/A5018248112","display_name":"Julien Pinquier","orcid":"https://orcid.org/0000-0003-1556-1284"},"institutions":[{"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"]},{"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":true,"raw_author_name":"J. Pinquier","raw_affiliation_strings":["Institut de Recherche en Informatique de Toulouse, UMR 5505 CNRS INP UPS, 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"]}]},{"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/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":"J.-L. Rouas","raw_affiliation_strings":["Institut de Recherche en Informatique de Toulouse, UMR 5505 CNRS INP UPS, 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"]}]},{"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"],"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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018248112"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I134560555","https://openalex.org/I4210119061"],"apc_list":null,"apc_paid":null,"fwci":1.1211,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.79678363,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"2","issue":null,"first_page":"II","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.8557999730110168,"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":0.8557999730110168,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.791100025177002,"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/speech-recognition","display_name":"Speech recognition","score":0.7183187007904053},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7002676725387573},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6607335209846497},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.6178112626075745},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6123563051223755},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4697414040565491},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4581202268600464},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4469003677368164},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4394238293170929},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.43305495381355286},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.42740699648857117},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41744983196258545},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07893919944763184}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7183187007904053},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7002676725387573},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6607335209846497},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.6178112626075745},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6123563051223755},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4697414040565491},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4581202268600464},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4469003677368164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4394238293170929},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.43305495381355286},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.42740699648857117},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41744983196258545},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07893919944763184},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2003.1202283","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1202283","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01695730v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01695730","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Acoustics, Speech and Signal Processing (ICASSP'2003), 2003, Hong Kong, China. pp.17-20, Vol. II, &#x27E8;10.1109/ICASSP.2003.1202283&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322892","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"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/W2115722710","https://openalex.org/W2124864596","https://openalex.org/W2128838222","https://openalex.org/W6607111733","https://openalex.org/W6607180710"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W2011227383","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W2065606036","https://openalex.org/W1526982611","https://openalex.org/W3021672241","https://openalex.org/W2147926259"],"abstract_inverted_index":{"We":[0],"present":[1],"and":[2,47,78,80,88,103,114],"merge":[3],"two":[4,69,75],"speech/music":[5,108],"classification":[6,62],"approaches":[7],"that":[8],"we":[9],"have":[10],"developed.":[11],"The":[12,33],"first":[13],"one":[14,35,94],"is":[15,26,36,64,72],"a":[16,22,65],"differentiated":[17],"modeling":[18],"approach":[19],"based":[20,37],"on":[21,38],"spectral":[23,101],"analysis,":[24],"which":[25],"implemented":[27],"using":[28],"GMM":[29],"(Gaussian":[30],"mixture":[31],"model).":[32],"other":[34],"three":[39],"original":[40],"features:":[41],"entropy":[42],"modulation,":[43],"stationary":[44],"segment":[45],"duration":[46],"number":[48],"of":[49,67,83,96],"segments.":[50],"They":[51],"are":[52],"merged":[53],"with":[54,93],"the":[55,68,100],"classical":[56],"4":[57],"Hertz":[58],"modulation":[59],"energy.":[60],"Our":[61],"system":[63],"fusion":[66],"approaches.":[70],"It":[71],"divided":[73],"in":[74,107],"classifications":[76],"(speech/non-speech":[77],"music/non-music)":[79],"provides":[81],"94%":[82],"accuracy":[84],"for":[85,90],"speech":[86],"detection":[87],"90%":[89],"music":[91],"detection,":[92],"second":[95],"input":[97],"signal.":[98],"Beside":[99],"information":[102],"GMM,":[104],"classically":[105],"used":[106],"discrimination,":[109],"simple":[110],"parameters":[111],"bring":[112],"complementary":[113],"efficient":[115],"information.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
