{"id":"https://openalex.org/W3092120053","doi":"https://doi.org/10.21437/interspeech.2020-2910","title":"Understanding the Effect of Voice Quality and Accent on Talker Similarity","display_name":"Understanding the Effect of Voice Quality and Accent on Talker Similarity","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3092120053","doi":"https://doi.org/10.21437/interspeech.2020-2910","mag":"3092120053"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2910","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5110452392","display_name":"Anurag Das","orcid":"https://orcid.org/0009-0007-9800-0699"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anurag Das","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078020198","display_name":"Guanlong Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guanlong Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078101671","display_name":"John M. Levis","orcid":"https://orcid.org/0000-0001-7405-5969"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John Levis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007545993","display_name":"Evgeny Chukharev\u2010Hudilainen","orcid":"https://orcid.org/0000-0001-7930-5787"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Evgeny Chukharev-Hudilainen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5062423099","display_name":"Ricardo Guti\u00e9rrez\u2010Osuna","orcid":"https://orcid.org/0000-0003-2817-2085"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ricardo Gutierrez-Osuna","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5416,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.74219637,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1763","last_page":"1767"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9947999715805054,"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/T12031","display_name":"Speech and dialogue systems","score":0.9941999912261963,"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/stress","display_name":"Stress (linguistics)","score":0.7119801640510559},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6666356325149536},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6636781096458435},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6595820188522339},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5413635969161987},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5017542839050293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37462806701660156}],"concepts":[{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7119801640510559},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6666356325149536},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6636781096458435},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6595820188522339},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5413635969161987},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5017542839050293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37462806701660156},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-2910","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:lib.dr.iastate.edu:engl_pubs-1283","is_oa":false,"landing_page_url":"https://lib.dr.iastate.edu/cgi/viewcontent.cgi?article=1283&context=engl_pubs","pdf_url":null,"source":{"id":"https://openalex.org/S4377196104","display_name":"Iowa State University Digital Repository (Iowa State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173911158","host_organization_name":"Iowa State University","host_organization_lineage":["https://openalex.org/I173911158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"English Publications","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1509691205","https://openalex.org/W1545150940","https://openalex.org/W1976466220","https://openalex.org/W2020304287","https://openalex.org/W2026369565","https://openalex.org/W2030351702","https://openalex.org/W2059265105","https://openalex.org/W2118154032","https://openalex.org/W2120605154","https://openalex.org/W2121387787","https://openalex.org/W2138643737","https://openalex.org/W2144832480","https://openalex.org/W2156477760","https://openalex.org/W2164843960","https://openalex.org/W2170282651","https://openalex.org/W2171019095","https://openalex.org/W2332809169","https://openalex.org/W2334284137","https://openalex.org/W2400588950","https://openalex.org/W2471520273","https://openalex.org/W2512149115","https://openalex.org/W2576309025","https://openalex.org/W2675443237","https://openalex.org/W2749170691","https://openalex.org/W2758155666","https://openalex.org/W2897092629","https://openalex.org/W2955237921","https://openalex.org/W2972633817","https://openalex.org/W2973142754"],"related_works":["https://openalex.org/W4367680763","https://openalex.org/W2739335048","https://openalex.org/W1506224037","https://openalex.org/W4213177143","https://openalex.org/W2151922127","https://openalex.org/W4237818736","https://openalex.org/W4252005663","https://openalex.org/W2365914832","https://openalex.org/W2352261042","https://openalex.org/W2314218554"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,20,29,32,39,59,102],"methodology":[4,18],"to":[5,24,45,89],"study":[6],"the":[7,26,47,91,113,130,137,143],"role":[8],"of":[9,28,35,50,61,96,115,125,146],"nonnative":[10],"accents":[11],"on":[12,55],"talker":[13],"recognition":[14],"by":[15],"humans.":[16],"The":[17],"combines":[19],"state-of-the-art":[21],"accent-conversion":[22],"system":[23],"resynthesize":[25],"voice":[27,53,116],"speaker":[30,56],"with":[31,76,82],"different":[33,72],"accent":[34,51,68],"her/his":[36],"own,":[37],"and":[38,52,63,79,128,152],"protocol":[40],"for":[41],"perceptual":[42],"listening":[43],"tests":[44],"measure":[46],"relative":[48],"contribution":[49],"quality":[54,117],"similarity.":[57],"Using":[58,101],"corpus":[60],"non-native":[62,74,83,126],"native":[64,77,80],"speakers,":[65],"we":[66,86,107],"generated":[67],"conversions":[69],"in":[70,149],"two":[71],"directions:":[73],"speakers":[75,81,135],"accents,":[78],"accents.":[84],"Then,":[85],"asked":[87],"listeners":[88],"rate":[90],"similarity":[92],"between":[93],"50":[94],"pairs":[95],"real":[97],"or":[98],"synthesized":[99],"speakers.":[100],"linear":[103],"mixed":[104],"effects":[105],"model,":[106],"find":[108],"that":[109,124,129],"(for":[110],"our":[111],"corpus)":[112],"effect":[114,131],"is":[118],"five":[119],"times":[120],"as":[121,123],"large":[122],"accent,":[127],"goes":[132],"away":[133],"when":[134],"share":[136],"same":[138],"(native)":[139],"accent.":[140],"We":[141],"discuss":[142],"potential":[144],"significance":[145],"this":[147],"work":[148],"earwitness":[150],"identification":[151],"sociophonetics.":[153]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}