{"id":"https://openalex.org/W2120731853","doi":"https://doi.org/10.1109/icassp.2009.4960576","title":"Applying improved spectral modeling for High Quality voice conversion","display_name":"Applying improved spectral modeling for High Quality voice conversion","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2120731853","doi":"https://doi.org/10.1109/icassp.2009.4960576","mag":"2120731853"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960576","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/A5020219878","display_name":"Fernando Villavicencio","orcid":null},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Fernando Villavicencio","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain","Music Technology Group, Universitat Pompeu Fabra, Ocata 1, 08003 Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Ocata 1, 08003 Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108509054","display_name":"Axel R\u00f6bel","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Axel Robel","raw_affiliation_strings":["IRCAM-CNRS-STMS, Paris, France","IRCAM-CNRS-STMS, Analysis-Synthesis Team, Place Igor Stravinsky, 75004 Paris, France#TAB#"],"affiliations":[{"raw_affiliation_string":"IRCAM-CNRS-STMS, Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I4389425508","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"IRCAM-CNRS-STMS, Analysis-Synthesis Team, Place Igor 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/A5113753026","display_name":"Xavier Rodet","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"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/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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Xavier Rodet","raw_affiliation_strings":["IRCAM-CNRS-STMS, Paris, France","IRCAM-CNRS-STMS, Analysis-Synthesis Team, Place Igor Stravinsky, 75004 Paris, France#TAB#"],"affiliations":[{"raw_affiliation_string":"IRCAM-CNRS-STMS, Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I4389425508","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"IRCAM-CNRS-STMS, Analysis-Synthesis Team, Place Igor Stravinsky, 75004 Paris, France#TAB#","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I4389425508","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020219878"],"corresponding_institution_ids":["https://openalex.org/I170486558"],"apc_list":null,"apc_paid":null,"fwci":2.1148,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.87227709,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"62","issue":null,"first_page":"4285","last_page":"4288"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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":0.9994000196456909,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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/spectral-envelope","display_name":"Spectral envelope","score":0.8611235022544861},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6413488388061523},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6031742095947266},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.536724328994751},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5357993841171265},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.5327643752098083},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.5298982262611389},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.46993833780288696},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.41637247800827026},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2867729663848877},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23742812871932983},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11019182205200195},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09764841198921204},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09659045934677124}],"concepts":[{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.8611235022544861},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6413488388061523},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6031742095947266},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.536724328994751},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5357993841171265},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.5327643752098083},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.5298982262611389},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.46993833780288696},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.41637247800827026},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2867729663848877},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23742812871932983},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11019182205200195},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09764841198921204},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09659045934677124},{"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/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4960576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960576","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":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1901696025","https://openalex.org/W2092233629","https://openalex.org/W2114352222","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2154291215","https://openalex.org/W2156142001","https://openalex.org/W2166537533","https://openalex.org/W2760715415","https://openalex.org/W4246413347"],"related_works":["https://openalex.org/W1499296618","https://openalex.org/W2062136349","https://openalex.org/W4232277401","https://openalex.org/W4313645560","https://openalex.org/W1986860206","https://openalex.org/W2145944162","https://openalex.org/W254868496","https://openalex.org/W654690113","https://openalex.org/W2073905179","https://openalex.org/W2171036255"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"accurate":[3],"spectral":[4,32,76,85],"envelope":[5,81],"estimation":[6],"is":[7,68],"applied":[8],"to":[9,14,27,34,70,96],"voice":[10],"conversion":[11,77,86],"in":[12,55],"order":[13,24,54],"achieve":[15],"high-quality":[16],"timbre":[17],"conversion.":[18],"True-envelope":[19],"based":[20],"estimators":[21],"allow":[22],"model":[23,53],"selection":[25],"leading":[26],"an":[28],"adaptation":[29,50],"of":[30,37,51,57,74],"the":[31,35,38,52,58,72,75],"features":[33],"characteristics":[36],"speaker.":[39],"Optimal":[40],"residual":[41],"signals":[42],"can":[43],"also":[44],"be":[45],"computed":[46],"following":[47],"a":[48],"local":[49],"terms":[56],"F":[59],"<sub":[60],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[61],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">0</sub>":[62],".":[63],"A":[64],"new":[65],"perceptual":[66],"criteria":[67],"proposed":[69,80],"measure":[71],"impact":[73],"error.":[78],"The":[79],"models":[82],"show":[83],"improved":[84],"performance":[87],"as":[88,90],"well":[89],"increased":[91],"converted-speech":[92],"quality":[93],"when":[94],"compared":[95],"linear":[97],"prediction.":[98]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
