{"id":"https://openalex.org/W1552080667","doi":"https://doi.org/10.1109/ijcnn.2005.1556217","title":"Harmonic envelope prediction for realistic speech synthesis using kernel interpolation","display_name":"Harmonic envelope prediction for realistic speech synthesis using kernel interpolation","publication_year":2006,"publication_date":"2006-01-05","ids":{"openalex":"https://openalex.org/W1552080667","doi":"https://doi.org/10.1109/ijcnn.2005.1556217","mag":"1552080667"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2005.1556217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2005.1556217","pdf_url":null,"source":{"id":"https://openalex.org/S4363609022","display_name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","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":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","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/A5065189262","display_name":"Pierre-Alexandre Fournier","orcid":null},"institutions":[{"id":"https://openalex.org/I29607241","display_name":"\u00c9cole Normale Sup\u00e9rieure - PSL","ror":"https://ror.org/05a0dhs15","country_code":"FR","type":"funder","lineage":["https://openalex.org/I2746051580","https://openalex.org/I29607241"]},{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA","FR"],"is_corresponding":true,"raw_author_name":"P.-A. Fournier","raw_affiliation_strings":["Department of Electrical Engineering, \u00c9cole Polytechnique de Montr\u00e9al, Montreal, QUE, Canada","Dept. of Electr. Eng. Ecole Polytech. de Montreal, Que., Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, \u00c9cole Polytechnique de Montr\u00e9al, Montreal, QUE, Canada","institution_ids":["https://openalex.org/I45683168"]},{"raw_affiliation_string":"Dept. of Electr. Eng. Ecole Polytech. de Montreal, Que., Canada","institution_ids":["https://openalex.org/I29607241"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090465684","display_name":"Jean\u2010Jules Brault","orcid":null},"institutions":[{"id":"https://openalex.org/I29607241","display_name":"\u00c9cole Normale Sup\u00e9rieure - PSL","ror":"https://ror.org/05a0dhs15","country_code":"FR","type":"funder","lineage":["https://openalex.org/I2746051580","https://openalex.org/I29607241"]},{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA","FR"],"is_corresponding":false,"raw_author_name":"J.-J. Brault","raw_affiliation_strings":["Department of Electrical Engineering, \u00c9cole Polytechnique de Montr\u00e9al, Montreal, QUE, Canada","Dept. of Electr. Eng. Ecole Polytech. de Montreal, Que., Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, \u00c9cole Polytechnique de Montr\u00e9al, Montreal, QUE, Canada","institution_ids":["https://openalex.org/I45683168"]},{"raw_affiliation_string":"Dept. of Electr. Eng. Ecole Polytech. de Montreal, Que., Canada","institution_ids":["https://openalex.org/I29607241"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065189262"],"corresponding_institution_ids":["https://openalex.org/I29607241","https://openalex.org/I45683168"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10014728,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"2059","last_page":"2063"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9976999759674072,"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":0.9902999997138977,"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-synthesis","display_name":"Speech synthesis","score":0.6446955800056458},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6239771842956543},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.6111975312232971},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5846216082572937},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.5250741839408875},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.5158809423446655},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.46924829483032227},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4611840844154358},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4516148865222931},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.4501478672027588},{"id":"https://openalex.org/keywords/harmonics","display_name":"Harmonics","score":0.4149875342845917},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38470152020454407},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34511131048202515},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3334481120109558},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.22506144642829895},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08469271659851074},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07877528667449951}],"concepts":[{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6446955800056458},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6239771842956543},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.6111975312232971},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5846216082572937},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.5250741839408875},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.5158809423446655},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.46924829483032227},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4611840844154358},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4516148865222931},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.4501478672027588},{"id":"https://openalex.org/C188414643","wikidata":"https://www.wikidata.org/wiki/Q3001183","display_name":"Harmonics","level":3,"score":0.4149875342845917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38470152020454407},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34511131048202515},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3334481120109558},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.22506144642829895},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08469271659851074},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07877528667449951},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2005.1556217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2005.1556217","pdf_url":null,"source":{"id":"https://openalex.org/S4363609022","display_name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","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":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W191699902","https://openalex.org/W1480376833","https://openalex.org/W1537591278","https://openalex.org/W1557133539","https://openalex.org/W1571477232","https://openalex.org/W2115151446","https://openalex.org/W6607852825","https://openalex.org/W6634367950","https://openalex.org/W6677458166"],"related_works":["https://openalex.org/W2588431733","https://openalex.org/W2391796527","https://openalex.org/W2387179309","https://openalex.org/W4245668640","https://openalex.org/W2388979876","https://openalex.org/W2032960563","https://openalex.org/W2142993035","https://openalex.org/W205537210","https://openalex.org/W2161566404","https://openalex.org/W2899044948"],"abstract_inverted_index":{"Harmonic":[0],"and":[1,55,64,99],"noise":[2,56],"diphone":[3],"concatenation":[4],"is":[5,50,143],"a":[6,31,122],"proven":[7],"method":[8,32],"to":[9,33,67,78,92,131],"obtain":[10],"high-quality":[11],"speech":[12,152],"synthesis,":[13],"but":[14],"cannot":[15],"be":[16],"used":[17],"when":[18],"the":[19,26,69,80,96,100,105,132],"basis":[20],"corpus":[21,37],"does":[22],"not":[23],"contain":[24],"all":[25],"diphones":[27],"needed.":[28],"We":[29,59,88],"propose":[30],"complete":[34],"an":[35,53],"individual's":[36],"using":[38,85,111],"examples":[39],"from":[40,47],"other":[41,145],"corpora.":[42],"Parametrisation":[43],"of":[44,83,104,127],"five":[45],"vowels":[46,84,107],"different":[48],"speakers":[49],"done":[51],"with":[52],"harmonic":[54,70,81,128,134],"model":[57],"(HNM).":[58],"use":[60,89],"multi-frame":[61],"analysis":[62],"(MFA)":[63],"smoothing":[65],"kernels":[66,75,119],"estimate":[68],"power":[71],"spectrum":[72],"envelopes.":[73],"Different":[74],"are":[76,108],"compared":[77,130],"predict":[79],"envelopes":[82,98],"training":[86],"data.":[87],"euclidian":[90],"distance":[91],"measure":[93],"similarity":[94],"between":[95],"real":[97],"predicted":[101],"ones.":[102],"Synthesis":[103],"interpolated":[106],"then":[109],"performed":[110],"learned":[112],"optimal":[113],"parameters.":[114],"Our":[115],"results":[116],"show":[117],"Gaussian":[118],"can":[120],"achieve":[121],"1.8":[123],"dB":[124],"(34.4%)":[125],"reduction":[126],"distorsion":[129],"mean":[133],"envelope":[135],"estimator.":[136],"As":[137],"far":[138],"as":[139],"we":[140],"know,":[141],"there":[142],"no":[144],"literature":[146],"on":[147],"phoneme":[148],"prediction":[149],"for":[150],"realistic":[151],"synthesis.":[153]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}