{"id":"https://openalex.org/W2955237921","doi":"https://doi.org/10.1109/taslp.2019.2926754","title":"Using Phonetic Posteriorgram Based Frame Pairing for Segmental Accent Conversion","display_name":"Using Phonetic Posteriorgram Based Frame Pairing for Segmental Accent Conversion","publication_year":2019,"publication_date":"2019-07-07","ids":{"openalex":"https://openalex.org/W2955237921","doi":"https://doi.org/10.1109/taslp.2019.2926754","mag":"2955237921"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2926754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2926754","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5078020198","display_name":"Guanlong Zhao","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":"Guanlong Zhao","raw_affiliation_strings":["Department of Computer Science and Engineering, Texas A&M University, College Station, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-6059-4053","affiliations":[{"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, College Station, TX, USA"],"raw_orcid":null,"affiliations":[{"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":1.4461,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.8665952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"27","issue":"10","first_page":"1649","last_page":"1660"},"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":0.9988999962806702,"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":0.9947999715805054,"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/stress","display_name":"Stress (linguistics)","score":0.7669171094894409},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.755213737487793},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7086642384529114},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5948836207389832},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.4935663938522339},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.41912198066711426},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.4120936393737793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3560759425163269},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07581827044487}],"concepts":[{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7669171094894409},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.755213737487793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7086642384529114},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5948836207389832},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.4935663938522339},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41912198066711426},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.4120936393737793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3560759425163269},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07581827044487},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","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},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2019.2926754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2926754","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7599999904632568}],"awards":[{"id":"https://openalex.org/G730122504","display_name":null,"funder_award_id":"1619212","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7894167722","display_name":null,"funder_award_id":"1623750","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"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":69,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W114517082","https://openalex.org/W116902681","https://openalex.org/W198589515","https://openalex.org/W1494198834","https://openalex.org/W1509691205","https://openalex.org/W1533674189","https://openalex.org/W1975263686","https://openalex.org/W1991682319","https://openalex.org/W2004299580","https://openalex.org/W2009272428","https://openalex.org/W2017425464","https://openalex.org/W2017742648","https://openalex.org/W2020304287","https://openalex.org/W2022241205","https://openalex.org/W2023407680","https://openalex.org/W2023728986","https://openalex.org/W2026369565","https://openalex.org/W2039679461","https://openalex.org/W2047706895","https://openalex.org/W2051140854","https://openalex.org/W2058624789","https://openalex.org/W2090823093","https://openalex.org/W2111898715","https://openalex.org/W2114659828","https://openalex.org/W2118154032","https://openalex.org/W2120259007","https://openalex.org/W2120605154","https://openalex.org/W2121387787","https://openalex.org/W2124331435","https://openalex.org/W2130942839","https://openalex.org/W2131062138","https://openalex.org/W2134714641","https://openalex.org/W2139246688","https://openalex.org/W2156477760","https://openalex.org/W2157259375","https://openalex.org/W2158069733","https://openalex.org/W2160815625","https://openalex.org/W2168473804","https://openalex.org/W2171019095","https://openalex.org/W2292984643","https://openalex.org/W2294038178","https://openalex.org/W2295119550","https://openalex.org/W2400588950","https://openalex.org/W2467997928","https://openalex.org/W2511006507","https://openalex.org/W2518312472","https://openalex.org/W2519648275","https://openalex.org/W2576309025","https://openalex.org/W2675443237","https://openalex.org/W2747744257","https://openalex.org/W2759071281","https://openalex.org/W2800962324","https://openalex.org/W2888954148","https://openalex.org/W2890402938","https://openalex.org/W2963035245","https://openalex.org/W2963808252","https://openalex.org/W2975109370","https://openalex.org/W6603838645","https://openalex.org/W6604828220","https://openalex.org/W6607999264","https://openalex.org/W6678683371","https://openalex.org/W6679436768","https://openalex.org/W6683276001","https://openalex.org/W6697024540","https://openalex.org/W6697090674","https://openalex.org/W6697163159","https://openalex.org/W6713218866","https://openalex.org/W6768203129"],"related_works":["https://openalex.org/W2079194684","https://openalex.org/W35292311","https://openalex.org/W2617269004","https://openalex.org/W2803166627","https://openalex.org/W2046073792","https://openalex.org/W153239700","https://openalex.org/W2067459736","https://openalex.org/W2105635394","https://openalex.org/W2151415191","https://openalex.org/W2151664070"],"abstract_inverted_index":{"Accent":[0],"conversion":[1,170,202],"(AC)":[2],"aims":[3],"to":[4,8,194],"transform":[5],"non-native":[6,38,124,156,183],"utterances":[7],"sound":[9],"as":[10],"if":[11],"the":[12,32,36,52,80,96,114,130,151,155,162,168,199],"speaker":[13,30],"had":[14],"a":[15,28,73,100,117,176,182],"native":[16,29,109,122,145,177],"accent.":[17,184],"This":[18],"can":[19,164,191],"be":[20,165,192],"achieved":[21],"by":[22],"mapping":[23],"source":[24],"speech":[25,118,174],"spectra":[26],"from":[27,95],"into":[31,99],"acoustic":[33,58,105,136],"space":[34],"of":[35,135,154],"target":[37],"speaker.":[39,157],"In":[40,68],"prior":[41,131],"work,":[42],"we":[43,71,92,159,186],"proposed":[44,127],"an":[45],"AC":[46],"approach":[47,75,115,163,190],"that":[48,76,161,188],"matches":[49,77],"frames":[50,78,94],"between":[51,79],"two":[53,81,97],"speakers":[54,82,98],"based":[55,83],"on":[56,84,108,116],"their":[57,85],"similarity":[59],"after":[60],"compensating":[61],"for":[62],"differences":[63],"in":[64,140,167],"vocal":[65],"tract":[66],"length.":[67],"this":[69,189],"paper,":[70],"propose":[72],"new":[74],"phonetic":[86,101],"(rather":[87],"than":[88],"acoustic)":[89],"similarity.":[90],"Namely,":[91],"map":[93],"posteriorgram":[102],"using":[103],"speaker-independent":[104],"models":[106],"trained":[107],"speech.":[110],"We":[111],"thoroughly":[112],"evaluate":[113],"corpus":[119],"containing":[120],"multiple":[121],"and":[123,144,181],"speakers.":[125],"The":[126],"algorithm":[128],"outperforms":[129],"approach,":[132],"improving":[133],"ratings":[134],"quality":[137,153,180],"(22%":[138],"increase":[139],"mean":[141],"opinion":[142],"score)":[143],"accent":[146,201],"(69%":[147],"preference)":[148],"while":[149],"retaining":[150],"voice":[152,179],"Furthermore,":[158],"show":[160,187],"used":[166],"reverse":[169],"direction,":[171],"i.e.,":[172],"generating":[173],"with":[175],"speaker's":[178],"Finally,":[185],"applied":[193],"non-parallel":[195],"training":[196],"data,":[197],"achieving":[198],"same":[200],"performance.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}