{"id":"https://openalex.org/W4319862665","doi":"https://doi.org/10.1109/slt54892.2023.10022506","title":"Remap, Warp and Attend: Non-Parallel Many-to-Many Accent Conversion with Normalizing Flows","display_name":"Remap, Warp and Attend: Non-Parallel Many-to-Many Accent Conversion with Normalizing Flows","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862665","doi":"https://doi.org/10.1109/slt54892.2023.10022506"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022506","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022506","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5027412678","display_name":"Abdelhamid Ezzerg","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Abdelhamid Ezzerg","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038417409","display_name":"Thomas Merritt","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Merritt","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047287498","display_name":"Kayoko Yanagisawa","orcid":"https://orcid.org/0000-0002-3444-7287"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kayoko Yanagisawa","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060480943","display_name":"Piotr Bili\u0144ski","orcid":"https://orcid.org/0000-0002-7023-3438"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piotr Bilinski","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036460629","display_name":"Magdalena Proszewska","orcid":"https://orcid.org/0000-0002-5523-2197"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I126596746","display_name":"Jagiellonian University","ror":"https://ror.org/03bqmcz70","country_code":"PL","type":"education","lineage":["https://openalex.org/I126596746"]}],"countries":["PL","US"],"is_corresponding":false,"raw_author_name":"Magdalena Proszewska","raw_affiliation_strings":["Amazon Alexa","Jagiellonian University, Poland"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Jagiellonian University, Poland","institution_ids":["https://openalex.org/I126596746"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000904701","display_name":"Kamil Pokora","orcid":"https://orcid.org/0009-0006-0756-4118"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kamil Pokora","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059545916","display_name":"Renard Korzeniowski","orcid":"https://orcid.org/0009-0004-8759-803X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Renard Korzeniowski","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027755752","display_name":"Roberto Barra-Chicote","orcid":"https://orcid.org/0000-0003-0844-7037"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roberto Barra-Chicote","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039620116","display_name":"Daniel Korzekwa","orcid":"https://orcid.org/0000-0003-1470-4968"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Korzekwa","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5027412678"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.2257,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.35294118,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"abs/2005. 09271","issue":null,"first_page":"984","last_page":"990"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.998199999332428,"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":0.9926000237464905,"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":0.8030257225036621},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7816582918167114},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.725687563419342},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6761834025382996},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5447607040405273},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.531385600566864},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4376258850097656},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4240085482597351},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3796598017215729}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8030257225036621},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7816582918167114},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.725687563419342},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6761834025382996},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5447607040405273},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.531385600566864},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4376258850097656},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4240085482597351},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3796598017215729},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/slt54892.2023.10022506","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022506","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1991682319","https://openalex.org/W2022241205","https://openalex.org/W2124331435","https://openalex.org/W2125047278","https://openalex.org/W2395403337","https://openalex.org/W2576309025","https://openalex.org/W2747874407","https://openalex.org/W2890402938","https://openalex.org/W2897353073","https://openalex.org/W2912298597","https://openalex.org/W2945478979","https://openalex.org/W2947196194","https://openalex.org/W2962788625","https://openalex.org/W2963035245","https://openalex.org/W2972970915","https://openalex.org/W2973142754","https://openalex.org/W2983786745","https://openalex.org/W2992005611","https://openalex.org/W3015282541","https://openalex.org/W3022876224","https://openalex.org/W3025528898","https://openalex.org/W3026874504","https://openalex.org/W3099078140","https://openalex.org/W3135654121","https://openalex.org/W3161492781","https://openalex.org/W3162770051","https://openalex.org/W3178546316","https://openalex.org/W3196584150","https://openalex.org/W4225316945","https://openalex.org/W4287776895","https://openalex.org/W4288337064","https://openalex.org/W6758706709","https://openalex.org/W6762533536","https://openalex.org/W6777327638","https://openalex.org/W6777694618","https://openalex.org/W6778083308"],"related_works":["https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W169399214","https://openalex.org/W1604114751","https://openalex.org/W4252942110","https://openalex.org/W2032941915","https://openalex.org/W2071315723","https://openalex.org/W2075706796","https://openalex.org/W2507083698","https://openalex.org/W3100825170"],"abstract_inverted_index":{"Regional":[0],"accents":[1],"of":[2,21,62,90,96,108,129],"the":[3,50,56,60,63,69,117,132],"same":[4],"language":[5],"affect":[6],"not":[7],"only":[8],"how":[9],"words":[10],"are":[11],"pronounced":[12],"(i.e.,":[13],"phonetic":[14,51,92],"content),":[15],"but":[16],"also":[17],"impact":[18],"prosodic":[19,94],"aspects":[20,95],"speech":[22,82,97,104],"such":[23],"as":[24],"speaking":[25],"rate":[26],"and":[27,72,80,93,102,112,136],"intonation.":[28],"This":[29],"paper":[30],"investigates":[31],"a":[32,122],"novel":[33],"flow-based":[34],"approach":[35,44,119],"to":[36,53,66,106,131],"accent":[37],"conversion":[38],"using":[39],"normalizing":[40],"flows.":[41],"The":[42,84],"proposed":[43,85,118],"revolves":[45],"around":[46],"three":[47],"steps:":[48],"remapping":[49],"conditioning,":[52],"better":[54,67],"match":[55],"target":[57,70,81,133],"accent,":[58,134],"warping":[59],"duration":[61],"converted":[64,103],"speech,":[65],"suit":[68],"phonemes,":[71],"an":[73],"attention":[74],"mechanism":[75],"that":[76,116],"implicitly":[77],"aligns":[78],"source":[79,101],"sequences.":[83],"remap-warp-attend":[86],"system":[87],"enables":[88],"adaptation":[89],"both":[91],"while":[98],"allowing":[99],"for":[100],"signals":[105],"be":[107],"different":[109],"lengths.":[110],"Objective":[111],"subjective":[113],"evaluations":[114],"show":[115],"significantly":[120],"outperforms":[121],"competitive":[123],"CopyCat":[124],"baseline":[125],"model":[126],"in":[127],"terms":[128],"similarity":[130],"naturalness":[135],"intelligibility.":[137]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}