{"id":"https://openalex.org/W1991682319","doi":"https://doi.org/10.1109/icassp.2014.6855134","title":"Can voice conversion be used to reduce non-native accents?","display_name":"Can voice conversion be used to reduce non-native accents?","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W1991682319","doi":"https://doi.org/10.1109/icassp.2014.6855134","mag":"1991682319"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6855134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6855134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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":null,"display_name":"Sandesh Aryal","orcid":null},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sandesh Aryal","raw_affiliation_strings":["Department of Computer Science and Engineering, Texas A&M University, USA","Department of Computer Science and Engineering, Texas A&M University , College Station, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Texas A&M University, USA","institution_ids":["https://openalex.org/I91045830"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Texas A&M University , College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062423099","display_name":"Ricardo Guti\u00e9rrez\u2010Osuna","orcid":"https://orcid.org/0000-0003-2817-2085"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ricardo Gutierrez-Osuna","raw_affiliation_strings":["Department of Computer Science and Engineering, Texas A&M University, USA","Department of Computer Science and Engineering, Texas A&M University , College Station, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Texas A&M University, USA","institution_ids":["https://openalex.org/I91045830"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Texas A&M University , College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.652,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.94832934,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7879","last_page":"7883"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.995199978351593,"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":0.7850116491317749},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7205061316490173},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.6134369373321533},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5320217609405518},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5275321006774902},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4965265393257141},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49322956800460815},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3615243434906006},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0774776041507721},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.07185599207878113}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7850116491317749},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7205061316490173},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.6134369373321533},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5320217609405518},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5275321006774902},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4965265393257141},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49322956800460815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3615243434906006},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0774776041507721},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.07185599207878113},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6855134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6855134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W78307492","https://openalex.org/W102979914","https://openalex.org/W1926768285","https://openalex.org/W1971596446","https://openalex.org/W1982854652","https://openalex.org/W2017742648","https://openalex.org/W2023728986","https://openalex.org/W2062308804","https://openalex.org/W2111898715","https://openalex.org/W2118850452","https://openalex.org/W2120605154","https://openalex.org/W2124331435","https://openalex.org/W2139246688","https://openalex.org/W2143076222","https://openalex.org/W2157259375","https://openalex.org/W2240197962","https://openalex.org/W2428180336","https://openalex.org/W6683276001","https://openalex.org/W6689899435"],"related_works":["https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W2174706483","https://openalex.org/W2997121352","https://openalex.org/W419536403","https://openalex.org/W2506280730","https://openalex.org/W4237969969","https://openalex.org/W1594297642","https://openalex.org/W2366328218","https://openalex.org/W2509366663"],"abstract_inverted_index":{"Voice-conversion":[0],"(VC)":[1],"techniques":[2],"aim":[3],"to":[4,11,36,69],"transform":[5],"utterances":[6],"from":[7],"a":[8,15,57,88,108,122],"source":[9,43,78],"speaker":[10,17],"sound":[12],"as":[13,71,91],"if":[14],"target":[16,80],"had":[18],"produced":[19],"them.":[20],"For":[21],"this":[22,53],"reason,":[23],"VC":[24,65,120],"is":[25,35,92],"generally":[26],"ill-suited":[27],"for":[28,64],"accent-conversion":[29],"(AC)":[30],"purposes,":[31],"where":[32],"the":[33,38,42,46,50,60,105,134,143,146],"goal":[34],"capture":[37],"regional":[39],"accent":[40],"of":[41,49,59,124,145],"while":[44],"preserving":[45],"voice":[47],"quality":[48],"target.":[51],"In":[52],"paper,":[54],"we":[55,76],"propose":[56],"modification":[58],"conventional":[61,119],"training":[62],"process":[63],"that":[66],"allows":[67],"it":[68,117],"perform":[70],"an":[72],"AC":[73],"transform.":[74],"Namely,":[75],"pair":[77],"and":[79,112,115,138],"vectors":[81],"based":[82,98],"not":[83],"on":[84,99,107],"their":[85,100],"ordering":[86],"within":[87],"parallel":[89],"corpus,":[90],"commonly":[93],"done":[94],"in":[95],"VC,":[96],"but":[97],"linguistic":[101],"similarity.":[102],"We":[103,127],"validate":[104],"approach":[106],"corpus":[109],"containing":[110],"native-accented":[111],"Spanish-accented":[113],"utterances,":[114],"compare":[116],"against":[118],"through":[121],"series":[123],"listening":[125],"tests.":[126],"also":[128],"analyze":[129],"whether":[130],"phonological":[131],"differences":[132],"between":[133],"two":[135,147],"languages":[136],"(Spanish":[137],"American":[139],"English)":[140],"help":[141],"predict":[142],"performance":[144],"methods.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}