{"id":"https://openalex.org/W3208546454","doi":"https://doi.org/10.1109/sped53181.2021.9587350","title":"Autoregressive Articulatory WaveNet Flow for Speaker-Independent Acoustic-to-Articulatory Inversion","display_name":"Autoregressive Articulatory WaveNet Flow for Speaker-Independent Acoustic-to-Articulatory Inversion","publication_year":2021,"publication_date":"2021-10-13","ids":{"openalex":"https://openalex.org/W3208546454","doi":"https://doi.org/10.1109/sped53181.2021.9587350","mag":"3208546454"},"language":"en","primary_location":{"id":"doi:10.1109/sped53181.2021.9587350","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped53181.2021.9587350","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","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/A5033165110","display_name":"Narjes Bozorg","orcid":null},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Narjes Bozorg","raw_affiliation_strings":["Electrical and Computer Engineering, University of Kentucky, Lexington, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of Kentucky, Lexington, USA","institution_ids":["https://openalex.org/I143302722"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015797517","display_name":"Michael T. Johnson","orcid":"https://orcid.org/0000-0001-5424-4877"},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael T. Johnson","raw_affiliation_strings":["Electrical and Computer Engineering, University of Kentucky, Lexington, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of Kentucky, Lexington, USA","institution_ids":["https://openalex.org/I143302722"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064273942","display_name":"Mohammad Soleymanpour","orcid":null},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Soleymanpour","raw_affiliation_strings":["Electrical and Computer Engineering, University of Kentucky, Lexington, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of Kentucky, Lexington, USA","institution_ids":["https://openalex.org/I143302722"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033165110"],"corresponding_institution_ids":["https://openalex.org/I143302722"],"apc_list":null,"apc_paid":null,"fwci":0.136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.560212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"abs 1609 3499","issue":null,"first_page":"156","last_page":"161"},"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":0.9994000196456909,"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":0.9987000226974487,"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":0.7394826412200928},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6664813160896301},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.6228874921798706},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5646007061004639},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.49330559372901917},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.46429571509361267},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.35076552629470825},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.215423583984375},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09890881180763245},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07864740490913391},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.06665864586830139}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7394826412200928},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6664813160896301},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.6228874921798706},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5646007061004639},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.49330559372901917},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.46429571509361267},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.35076552629470825},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.215423583984375},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09890881180763245},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07864740490913391},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.06665864586830139},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sped53181.2021.9587350","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped53181.2021.9587350","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W179282036","https://openalex.org/W201148316","https://openalex.org/W1525807100","https://openalex.org/W1531956331","https://openalex.org/W1562842113","https://openalex.org/W1564657563","https://openalex.org/W1788348338","https://openalex.org/W1982854652","https://openalex.org/W2006775235","https://openalex.org/W2026149420","https://openalex.org/W2041823554","https://openalex.org/W2069618035","https://openalex.org/W2105478683","https://openalex.org/W2134539847","https://openalex.org/W2141697795","https://openalex.org/W2159693968","https://openalex.org/W2231075402","https://openalex.org/W2395955767","https://openalex.org/W2460967393","https://openalex.org/W2509129594","https://openalex.org/W2519091744","https://openalex.org/W2559246505","https://openalex.org/W2603829373","https://openalex.org/W2748883834","https://openalex.org/W2757361640","https://openalex.org/W2787248829","https://openalex.org/W2888815947","https://openalex.org/W2888898948","https://openalex.org/W2940009604","https://openalex.org/W2943899479","https://openalex.org/W2944489095","https://openalex.org/W2944526294","https://openalex.org/W2953184570","https://openalex.org/W2963464520","https://openalex.org/W2963782041","https://openalex.org/W2972363853","https://openalex.org/W2972916618","https://openalex.org/W2983060947","https://openalex.org/W3005960869","https://openalex.org/W3008195600","https://openalex.org/W4294619240","https://openalex.org/W4298642009","https://openalex.org/W6607366425","https://openalex.org/W6608180490","https://openalex.org/W6631452893","https://openalex.org/W6638094663","https://openalex.org/W6689608924","https://openalex.org/W6711834147","https://openalex.org/W6736176328","https://openalex.org/W6744071827","https://openalex.org/W6843673214","https://openalex.org/W6844105982"],"related_works":["https://openalex.org/W1887737739","https://openalex.org/W2384978429","https://openalex.org/W3095903107","https://openalex.org/W2042455139","https://openalex.org/W239487380","https://openalex.org/W326551381","https://openalex.org/W17819389","https://openalex.org/W3214626309","https://openalex.org/W4368276095","https://openalex.org/W3036459603"],"abstract_inverted_index":{"In":[0],"this":[1,118],"paper":[2],"we":[3],"introduce":[4],"a":[5,124],"new":[6],"speaker":[7],"independent":[8],"method":[9,108],"for":[10,41],"Acoustic-to-Articulatory":[11,134],"Inversion.":[12],"The":[13,84],"proposed":[14,48],"architecture,":[15],"Speaker":[16,105,132],"Independent-Articulatory":[17],"WaveNet":[18],"(SI-AWN),":[19],"models":[20],"the":[21,30,39,47,51,62,90,93,99,113,120,129,144],"relationship":[22],"between":[23],"acoustic":[24,34],"and":[25,36,71,81,136],"articulatory":[26,31],"features":[27,35],"by":[28,109],"conditioning":[29],"trajectories":[32],"on":[33,50,73],"then":[37],"utilizes":[38],"structure":[40],"unseen":[42],"target":[43,74],"speakers.":[44,83],"We":[45],"evaluate":[46],"SI-AWN":[49,88],"Electro":[52],"Magnetic":[53],"Articulography":[54],"corpus":[55],"of":[56,64,92,115,123,131],"Mandarin":[57],"Accented":[58],"English":[59],"(EMA-MAE),":[60],"using":[61],"pool":[63],"acoustic-articulatory":[65],"information":[66],"from":[67],"35":[68],"reference":[69],"speakers":[70,75],"testing":[72],"that":[76,87],"include":[77],"male,":[78],"female,":[79],"native":[80],"non-native":[82],"results":[85,137],"suggest":[86],"improves":[89],"performance":[91],"acoustic-to-articulatory":[94],"inversion":[95],"process":[96],"compared":[97],"to":[98,128,140],"baseline":[100],"Maximum":[101],"Likelihood":[102],"Regression-Parallel":[103],"Reference":[104],"Weighting":[106],"(MLLR-PRSW)":[107],"21":[110],"percent.":[111],"To":[112],"best":[114,145],"our":[116],"knowledge,":[117],"is":[119],"first":[121],"application":[122],"WaveNet-like":[125],"synthesis":[126],"approach":[127],"problem":[130],"Independent":[133],"Inversion,":[135],"are":[138],"comparable":[139],"or":[141],"better":[142],"than":[143],"currently":[146],"published":[147],"systems.":[148]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}