{"id":"https://openalex.org/W2123169318","doi":"https://doi.org/10.1109/icassp.2009.4959926","title":"Singing voice detection in music tracks using direct voice vibrato detection","display_name":"Singing voice detection in music tracks using direct voice vibrato detection","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2123169318","doi":"https://doi.org/10.1109/icassp.2009.4959926","mag":"2123169318"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4959926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4959926","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":"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/A5016269775","display_name":"Lise Regnier","orcid":null},"institutions":[{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I4210143563","display_name":"Laboratoire de Synth\u00e8se Organique","ror":"https://ror.org/04qgfge56","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I142476485","https://openalex.org/I201181511","https://openalex.org/I4210128300","https://openalex.org/I4210143563","https://openalex.org/I4210145102","https://openalex.org/I4210145102","https://openalex.org/I4405258625"]},{"id":"https://openalex.org/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":null,"type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]},{"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":"L. Regnier","raw_affiliation_strings":["Sound Analysis/ Synthesis team, CNRS-STMS, I. R. C. A. M., Paris, France","IRCAM, Sound Analysis/ Synthesis team, CNRS-STMS, 1 place Stravinsky, 75004 Paris, France#TAB#"],"affiliations":[{"raw_affiliation_string":"Sound Analysis/ Synthesis team, CNRS-STMS, I. R. C. A. M., Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I4210143563","https://openalex.org/I4389425508","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"IRCAM, Sound Analysis/ Synthesis team, CNRS-STMS, 1 place Stravinsky, 75004 Paris, France#TAB#","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I4389425508","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063097936","display_name":"Geoffroy Peeters","orcid":"https://orcid.org/0000-0001-5255-3019"},"institutions":[{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":null,"type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]},{"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/I4210143563","display_name":"Laboratoire de Synth\u00e8se Organique","ror":"https://ror.org/04qgfge56","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I142476485","https://openalex.org/I201181511","https://openalex.org/I4210128300","https://openalex.org/I4210143563","https://openalex.org/I4210145102","https://openalex.org/I4210145102","https://openalex.org/I4405258625"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"G. Peeters","raw_affiliation_strings":["Sound Analysis/ Synthesis team, CNRS-STMS, I. R. C. A. M., Paris, France","IRCAM, Sound Analysis/ Synthesis team, CNRS-STMS, 1 place Stravinsky, 75004 Paris, France#TAB#"],"affiliations":[{"raw_affiliation_string":"Sound Analysis/ Synthesis team, CNRS-STMS, I. R. C. A. M., Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I4210143563","https://openalex.org/I4389425508","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"IRCAM, Sound Analysis/ Synthesis team, CNRS-STMS, 1 place Stravinsky, 75004 Paris, France#TAB#","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I4389425508","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5016269775"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I35345632","https://openalex.org/I4210143563","https://openalex.org/I4389425508"],"apc_list":null,"apc_paid":null,"fwci":7.4017,"has_fulltext":false,"cited_by_count":83,"citation_normalized_percentile":{"value":0.9788256,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"1","issue":null,"first_page":"1685","last_page":"1688"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9947999715805054,"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/vibrato","display_name":"Vibrato","score":0.969727635383606},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.911396861076355},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7405078411102295},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.7026583552360535},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6726121306419373},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4776296019554138},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.4627380967140198},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.43687495589256287},{"id":"https://openalex.org/keywords/frequency-modulation","display_name":"Frequency modulation","score":0.4353324770927429},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3855170011520386},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3563922047615051},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.350253164768219},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3398948013782501},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0905781090259552},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.0824899971485138}],"concepts":[{"id":"https://openalex.org/C2781100714","wikidata":"https://www.wikidata.org/wiki/Q377435","display_name":"Vibrato","level":3,"score":0.969727635383606},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.911396861076355},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7405078411102295},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.7026583552360535},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6726121306419373},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4776296019554138},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.4627380967140198},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.43687495589256287},{"id":"https://openalex.org/C11930861","wikidata":"https://www.wikidata.org/wiki/Q181417","display_name":"Frequency modulation","level":3,"score":0.4353324770927429},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3855170011520386},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3563922047615051},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.350253164768219},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3398948013782501},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0905781090259552},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0824899971485138},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"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":1,"locations":[{"id":"doi:10.1109/icassp.2009.4959926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4959926","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W65296863","https://openalex.org/W126277046","https://openalex.org/W1499705833","https://openalex.org/W1570504315","https://openalex.org/W1833279920","https://openalex.org/W1990346118","https://openalex.org/W2075905938","https://openalex.org/W2098796164","https://openalex.org/W2107707103","https://openalex.org/W2116849392","https://openalex.org/W2124867748","https://openalex.org/W2154591323","https://openalex.org/W2398970793","https://openalex.org/W6602647452","https://openalex.org/W6605095414","https://openalex.org/W6630060122","https://openalex.org/W6634309418","https://openalex.org/W6677506536","https://openalex.org/W6682825961","https://openalex.org/W6712548819","https://openalex.org/W7025302790"],"related_works":["https://openalex.org/W2001832747","https://openalex.org/W2024403596","https://openalex.org/W4394924759","https://openalex.org/W2886940211","https://openalex.org/W1850879794","https://openalex.org/W4394925019","https://openalex.org/W1583791393","https://openalex.org/W2047861854","https://openalex.org/W2057725539","https://openalex.org/W2405700924"],"abstract_inverted_index":{"In":[0,35,52],"this":[1,21,113,195],"paper":[2],"we":[3,23,38,56,67,114],"investigate":[4],"the":[5,26,29,41,53,60,73,95,103,119,123,126,169,200,223],"problem":[6],"of":[7,28,86,122,129,131,168,194],"locating":[8],"singing":[9,33,42,99,110,164],"voice":[10,43,100],"in":[11,174],"music":[12],"tracks.":[13],"As":[14],"opposed":[15],"to":[16,32,92,98,108,176,199,222,230],"most":[17],"existing":[18],"methods":[19],"for":[20,116],"task,":[22],"rely":[24],"on":[25,143,150,156,186],"extraction":[27],"characteristics":[30],"specific":[31],"voice.":[34,111],"our":[36],"approach":[37,208,226],"suppose":[39],"that":[40],"is":[44,106,139,152,171,183,237],"characterized":[45],"by":[46],"harmonicity,":[47],"formants,":[48],"vibrato":[49,61,133],"and":[50,62,82,101,125,134,210,245],"tremolo.":[51,135],"present":[54],"study":[55],"deal":[57],"only":[58],"with":[59,203,213],"tremolo":[63],"characteristics.":[64],"For":[65,112],"this,":[66,157],"first":[68],"extract":[69],"sinusoidal":[70],"partials":[71],"from":[72],"musical":[74],"audio":[75],"signal":[76],".":[77],"The":[78,180,192,215],"frequency":[79],"modulation":[80,84],"(vibrato)":[81],"amplitude":[83],"(tremolo)":[85],"each":[87,117,158],"partial":[88,96,118,137],"are":[89,197,243],"then":[90,140,172,184,247],"studied":[91],"determine":[93],"if":[94],"corresponds":[97],"hence":[102],"corresponding":[104],"segment":[105,159],"supposed":[107],"contain":[109],"estimate":[115],"rate":[120],"(frequency":[121],"modulations)":[124],"extent":[127],"(amplitude":[128],"modulation)":[130],"both":[132,241],"A":[136,146],"selection":[138],"operated":[141],"based":[142,149],"these":[144],"values.":[145],"second":[147],"criteria":[148],"harmonicity":[151],"also":[153],"introduced.":[154],"Based":[155],"can":[160,246],"be":[161,248],"labelled":[162],"as":[163],"or":[165],"non-singing.":[166],"Post-processing":[167],"segmentation":[170],"applied":[173],"order":[175],"remove":[177],"short-duration":[178],"segments.":[179],"proposed":[181,216],"method":[182,217],"evaluated":[185],"a":[187,204],"large":[188],"manually":[189],"annotated":[190],"test-set.":[191],"results":[193,221],"evaluation":[196],"compared":[198,229],"one":[201],"obtained":[202],"usual":[205],"machine":[206,224],"learning":[207,225],"(MFCC":[209],"SFM":[211],"modeling":[212],"GMM).":[214],"achieves":[218],"very":[219,238],"close":[220],":":[227],"76.8%":[228],"77.4%":[231],"F-measure":[232],"(frame":[233],"classification).":[234],"This":[235],"result":[236],"promising,":[239],"since":[240],"approaches":[242],"orthogonal":[244],"combined.":[249]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}