{"id":"https://openalex.org/W3015826722","doi":"https://doi.org/10.1109/icassp40776.2020.9054305","title":"Generating Multilingual Voices Using Speaker Space Translation Based on Bilingual Speaker Data","display_name":"Generating Multilingual Voices Using Speaker Space Translation Based on Bilingual Speaker Data","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015826722","doi":"https://doi.org/10.1109/icassp40776.2020.9054305","mag":"3015826722"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.04972","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010858961","display_name":"Soumi Maiti","orcid":"https://orcid.org/0000-0001-6940-0115"},"institutions":[{"id":"https://openalex.org/I121847817","display_name":"The Graduate Center, CUNY","ror":"https://ror.org/00awd9g61","country_code":"US","type":"education","lineage":["https://openalex.org/I121847817"]},{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soumi Maiti","raw_affiliation_strings":["The Graduate Center, CUNY, Apple, New York, NY","Apple,The Graduate Center, CUNY,New York,NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Graduate Center, CUNY, Apple, New York, NY","institution_ids":["https://openalex.org/I121847817","https://openalex.org/I4210153776"]},{"raw_affiliation_string":"Apple,The Graduate Center, CUNY,New York,NY","institution_ids":["https://openalex.org/I121847817","https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009327522","display_name":"Erik Marchi","orcid":"https://orcid.org/0000-0002-5335-6356"},"institutions":[{"id":"https://openalex.org/I121847817","display_name":"The Graduate Center, CUNY","ror":"https://ror.org/00awd9g61","country_code":"US","type":"education","lineage":["https://openalex.org/I121847817"]},{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erik Marchi","raw_affiliation_strings":["The Graduate Center, CUNY, Apple, New York, NY","Apple,The Graduate Center, CUNY,New York,NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Graduate Center, CUNY, Apple, New York, NY","institution_ids":["https://openalex.org/I121847817","https://openalex.org/I4210153776"]},{"raw_affiliation_string":"Apple,The Graduate Center, CUNY,New York,NY","institution_ids":["https://openalex.org/I121847817","https://openalex.org/I4210153776"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028548414","display_name":"Alistair Conkie","orcid":null},"institutions":[{"id":"https://openalex.org/I121847817","display_name":"The Graduate Center, CUNY","ror":"https://ror.org/00awd9g61","country_code":"US","type":"education","lineage":["https://openalex.org/I121847817"]},{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alistair Conkie","raw_affiliation_strings":["The Graduate Center, CUNY, Apple, New York, NY","Apple,The Graduate Center, CUNY,New York,NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Graduate Center, CUNY, Apple, New York, NY","institution_ids":["https://openalex.org/I121847817","https://openalex.org/I4210153776"]},{"raw_affiliation_string":"Apple,The Graduate Center, CUNY,New York,NY","institution_ids":["https://openalex.org/I121847817","https://openalex.org/I4210153776"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.23,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.46266818,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"17","issue":null,"first_page":"7624","last_page":"7628"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9933000206947327,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9896000027656555,"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/naturalness","display_name":"Naturalness","score":0.847716212272644},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6132184267044067},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6104514002799988},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5356850624084473},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5110024213790894},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4804955720901489},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.43151330947875977},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4261436462402344},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.413127064704895},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3569169342517853},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.301841139793396},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.26003992557525635},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.11959147453308105}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.847716212272644},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6132184267044067},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6104514002799988},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5356850624084473},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5110024213790894},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4804955720901489},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.43151330947875977},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4261436462402344},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.413127064704895},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3569169342517853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.301841139793396},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26003992557525635},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.11959147453308105},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2004.04972","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.04972","pdf_url":"https://arxiv.org/pdf/2004.04972","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3015826722","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2004.04972.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2004.04972","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2004.04972","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/2wjp-c906","is_oa":true,"landing_page_url":"https://doi.org/10.17023/2wjp-c906","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"},{"id":"doi:10.17023/7qez-ex43","is_oa":true,"landing_page_url":"https://doi.org/10.17023/7qez-ex43","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.04972","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.04972","pdf_url":"https://arxiv.org/pdf/2004.04972","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8299999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3015826722.pdf","grobid_xml":"https://content.openalex.org/works/W3015826722.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1731081199","https://openalex.org/W2064675550","https://openalex.org/W2089468765","https://openalex.org/W2114925438","https://openalex.org/W2157331557","https://openalex.org/W2187089797","https://openalex.org/W2401698713","https://openalex.org/W2471520273","https://openalex.org/W2748238740","https://openalex.org/W2794235490","https://openalex.org/W2801608439","https://openalex.org/W2950635152","https://openalex.org/W2957543415","https://openalex.org/W2963432880","https://openalex.org/W2963609956","https://openalex.org/W2963964591","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2972440097","https://openalex.org/W2972473628","https://openalex.org/W6631190155","https://openalex.org/W6637618735","https://openalex.org/W6748409065","https://openalex.org/W6752888775"],"related_works":["https://openalex.org/W3016090709","https://openalex.org/W3027127570","https://openalex.org/W2873019472","https://openalex.org/W3092657432","https://openalex.org/W279708261","https://openalex.org/W2937051792","https://openalex.org/W2828515060","https://openalex.org/W1806574086","https://openalex.org/W2277667770","https://openalex.org/W2185945743","https://openalex.org/W2957543415","https://openalex.org/W2302018922","https://openalex.org/W2482338111","https://openalex.org/W2408526116","https://openalex.org/W3127157320","https://openalex.org/W195231397","https://openalex.org/W2107201284","https://openalex.org/W1993687062","https://openalex.org/W2958167712","https://openalex.org/W2113998014"],"abstract_inverted_index":{"We":[0,24,107],"present":[1,164],"progress":[2],"towards":[3],"bilingual":[4,28,86],"Text-to-Speech":[5],"which":[6],"is":[7,170],"able":[8],"to":[9,14,55,75,94,98,104,115,122],"transform":[10,43,70,112,150],"a":[11,16,27,33,41,62,66,117,126,138,174],"monolingual":[12,76],"voice":[13,22,64,118,136,141],"speak":[15,99,105],"second":[17],"language":[18,38,121,140],"while":[19],"preserving":[20],"speaker":[21,29,45,50,80,87],"quality.":[23],"demonstrate":[25],"that":[26,40,109,148],"embedding":[30,51],"space":[31,46],"contains":[32],"separate":[34],"distribution":[35],"for":[36],"each":[37],"and":[39,90,101,168],"simple":[42,111],"in":[44,65,142],"generated":[47],"by":[48],"the":[49,57,91,110,123,134,149,154,157],"can":[52,71,165],"be":[53,72,166],"used":[54],"control":[56],"degree":[58,128,161],"of":[59,61,129,153,156,162,176],"accent":[60,163,177],"synthetic":[63],"language.":[67],"The":[68,160],"same":[69],"applied":[73],"even":[74],"speakers.In":[77],"our":[78],"experiments":[79],"data":[81],"from":[82,119],"an":[83],"English-Spanish":[84],"(Mexican)":[85],"was":[88,93,113],"used,":[89],"goal":[92],"enable":[95],"English":[96],"speakers":[97,103],"Spanish":[100,102],"English.":[106],"found":[108],"sufficient":[114],"convert":[116],"one":[120,132],"other":[124],"with":[125],"high":[127],"naturalness.":[130],"In":[131],"case":[133],"transformed":[135],"outperformed":[137],"native":[139],"listening":[143],"tests.":[144],"Experiments":[145],"further":[146],"indicated":[147],"preserved":[151],"many":[152],"characteristics":[155],"original":[158],"voice.":[159],"controlled":[167],"naturalness":[169],"relatively":[171],"consistent":[172],"across":[173],"range":[175],"values.":[178]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}