{"id":"https://openalex.org/W2125047278","doi":"https://doi.org/10.1109/icassp.2014.6855097","title":"Accent conversion through cross-speaker articulatory synthesis","display_name":"Accent conversion through cross-speaker articulatory synthesis","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2125047278","doi":"https://doi.org/10.1109/icassp.2014.6855097","mag":"2125047278"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6855097","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6855097","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","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","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","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","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":2.9604,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.92426691,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7694","last_page":"7698"},"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":0.9983999729156494,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.74048912525177},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7061725854873657},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.7034235000610352},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6495562791824341},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.47855764627456665},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4648318290710449},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4619237780570984},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.4146122634410858},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3288053274154663},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12630796432495117},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11447185277938843},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.07110753655433655}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.74048912525177},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7061725854873657},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7034235000610352},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6495562791824341},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.47855764627456665},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4648318290710449},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4619237780570984},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.4146122634410858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3288053274154663},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12630796432495117},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11447185277938843},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.07110753655433655},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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.2014.6855097","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6855097","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":0.8100000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W93060608","https://openalex.org/W1926768285","https://openalex.org/W1971596446","https://openalex.org/W1982854652","https://openalex.org/W1987297220","https://openalex.org/W1993533823","https://openalex.org/W2017742648","https://openalex.org/W2022241205","https://openalex.org/W2023728986","https://openalex.org/W2032988466","https://openalex.org/W2063036810","https://openalex.org/W2099750345","https://openalex.org/W2111701360","https://openalex.org/W2120605154","https://openalex.org/W2124331435","https://openalex.org/W2131127238","https://openalex.org/W2135707066","https://openalex.org/W2139246688","https://openalex.org/W2157259375","https://openalex.org/W2295518984","https://openalex.org/W2396135730","https://openalex.org/W2406017614","https://openalex.org/W6603807496","https://openalex.org/W6683276001","https://openalex.org/W6714191056"],"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/W4386784607"],"abstract_inverted_index":{"Accent":[0],"conversion":[1],"(AC)":[2],"seeks":[3],"to":[4,9,27,53,92,131],"transform":[5],"second-language":[6],"(L2)":[7],"utterances":[8],"appear":[10],"as":[11],"if":[12],"produced":[13],"with":[14,61,112,140],"a":[15,48,87,107,142],"native":[16],"(L1)":[17],"accent.":[18],"In":[19],"the":[20,28,43,59,104,133,137],"acoustic":[21,95,146],"domain,":[22],"AC":[23,38],"is":[24,72],"difficult":[25],"due":[26],"complex":[29],"interaction":[30],"between":[31],"linguistic":[32],"content":[33],"and":[34,56,129],"voice":[35,134],"quality.":[36,147],"Alternatively,":[37],"can":[39],"be":[40],"performed":[41],"in":[42,124,145],"articulatory":[44,66,100,109],"domain":[45],"by":[46],"building":[47],"mapping":[49,90],"from":[50,98],"L2":[51,54,70,94,113,138],"articulators":[52],"acoustics,":[55],"then":[57],"driving":[58],"model":[60],"L1":[62,99],"articulators.":[63,114],"However,":[64],"collecting":[65],"data":[67],"for":[68],"each":[69],"learner":[71],"impractical.":[73],"Here":[74],"we":[75],"propose":[76],"an":[77],"approach":[78],"that":[79,119],"avoids":[80],"this":[81],"expensive":[82],"step.":[83],"Our":[84],"method":[85],"builds":[86],"cross-speaker":[88],"forward":[89],"(CSFM)":[91],"generate":[93],"observations":[96],"directly":[97],"trajectories.":[101],"We":[102],"evaluated":[103],"CSFM":[105],"against":[106],"baseline":[108],"synthesizer":[110],"trained":[111],"Subjective":[115],"listening":[116],"tests":[117],"show":[118],"both":[120],"methods":[121],"perform":[122],"comparably":[123],"terms":[125],"of":[126,136],"accent":[127],"reduction":[128],"ability":[130],"preserve":[132],"quality":[135],"speaker,":[139],"only":[141],"small":[143],"impact":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}