{"id":"https://openalex.org/W2401456508","doi":"https://doi.org/10.1109/icassp.2016.7472752","title":"Language-independent acoustic cloning of HTS voices: A preliminary study","display_name":"Language-independent acoustic cloning of HTS voices: A preliminary study","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2401456508","doi":"https://doi.org/10.1109/icassp.2016.7472752","mag":"2401456508"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5053738270","display_name":"Carmen Magari\u00f1os","orcid":"https://orcid.org/0000-0003-3525-1304"},"institutions":[{"id":"https://openalex.org/I6289922","display_name":"Universidade de Vigo","ror":"https://ror.org/05rdf8595","country_code":"ES","type":"education","lineage":["https://openalex.org/I6289922"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Carmen Magarinos","raw_affiliation_strings":["Multimedia Technology Group (GTM), University of Vigo, Spain"],"affiliations":[{"raw_affiliation_string":"Multimedia Technology Group (GTM), University of Vigo, Spain","institution_ids":["https://openalex.org/I6289922"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039550354","display_name":"Daniel Erro","orcid":null},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]},{"id":"https://openalex.org/I110594554","display_name":"Ikerbasque","ror":"https://ror.org/01cc3fy72","country_code":"ES","type":"other","lineage":["https://openalex.org/I110594554"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Daniel Erro","raw_affiliation_strings":["IKERBASQUE - Aholab, University of the Basque Country, Bilbao, Spain"],"affiliations":[{"raw_affiliation_string":"IKERBASQUE - Aholab, University of the Basque Country, Bilbao, Spain","institution_ids":["https://openalex.org/I110594554","https://openalex.org/I169108374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083117756","display_name":"Eduardo Rodr\u00edguez Banga","orcid":"https://orcid.org/0000-0001-7989-4526"},"institutions":[{"id":"https://openalex.org/I6289922","display_name":"Universidade de Vigo","ror":"https://ror.org/05rdf8595","country_code":"ES","type":"education","lineage":["https://openalex.org/I6289922"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Eduardo R. Banga","raw_affiliation_strings":["Multimedia Technology Group (GTM), University of Vigo, Spain"],"affiliations":[{"raw_affiliation_string":"Multimedia Technology Group (GTM), University of Vigo, Spain","institution_ids":["https://openalex.org/I6289922"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053738270"],"corresponding_institution_ids":["https://openalex.org/I6289922"],"apc_list":null,"apc_paid":null,"fwci":0.84563064,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.88979843,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5615","last_page":"5619"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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":0.9916999936103821,"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/computer-science","display_name":"Computer science","score":0.7873585224151611},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7233461141586304},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.6062776446342468},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5921922326087952},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5454526543617249},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5273581147193909},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5235152840614319},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4894489347934723},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4704906940460205},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.41804829239845276},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33194994926452637},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18244868516921997},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1042504608631134}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7873585224151611},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7233461141586304},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.6062776446342468},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5921922326087952},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5454526543617249},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5273581147193909},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5235152840614319},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4894489347934723},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4704906940460205},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.41804829239845276},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33194994926452637},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18244868516921997},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1042504608631134},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W113498433","https://openalex.org/W1512429158","https://openalex.org/W1583154192","https://openalex.org/W1878590289","https://openalex.org/W1963637322","https://openalex.org/W1995565802","https://openalex.org/W2007062874","https://openalex.org/W2025638820","https://openalex.org/W2098380781","https://openalex.org/W2117418893","https://openalex.org/W2129142580","https://openalex.org/W2161476805","https://openalex.org/W2309282333","https://openalex.org/W2400063444","https://openalex.org/W2407281753","https://openalex.org/W4285719527","https://openalex.org/W6630838124","https://openalex.org/W6639371816","https://openalex.org/W6712610176","https://openalex.org/W6713618356"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2097963413","https://openalex.org/W2294335174","https://openalex.org/W2025614924","https://openalex.org/W3145575561","https://openalex.org/W1992908141","https://openalex.org/W175280642","https://openalex.org/W2688184458","https://openalex.org/W2147186888"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,38],"new":[4],"method":[5,55],"for":[6,25,31],"cross-lingual":[7],"speaker":[8,34,98],"adaptation":[9],"in":[10,44],"the":[11,26,32,45,51,81,87,96],"framework":[12],"of":[13],"HMM-based":[14],"speech":[15,43],"synthesis.":[16],"Taking":[17],"two":[18],"HTS":[19],"voice":[20,90],"models":[21,83],"as":[22,93],"input,":[23],"one":[24],"desired":[27],"language":[28,47],"and":[29,62,66],"another":[30],"aimed":[33],"identity,":[35],"it":[36],"yields":[37],"third":[39],"model":[40],"that":[41],"produces":[42],"target":[46,52,97],"while":[48],"sounding":[49],"like":[50],"speaker.":[53],"The":[54],"operates":[56],"at":[57],"segmental":[58],"level":[59],"(spectral":[60],"information":[61],"average":[63],"fundamental":[64],"frequency)":[65],"does":[67],"not":[68],"require":[69],"any":[70],"phonetic":[71],"or":[72],"linguistic":[73],"information.":[74],"Perceptual":[75],"evaluation":[76],"experiments":[77],"show":[78],"that,":[79],"when":[80],"input":[82],"are":[84],"good":[85],"enough,":[86],"resulting":[88],"synthetic":[89],"is":[91],"perceived":[92],"similar":[94],"to":[95],"with":[99],"no":[100],"important":[101],"quality":[102],"degradation.":[103]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}