{"id":"https://openalex.org/W4385987299","doi":"https://doi.org/10.21437/slate.2023-14","title":"Towards Acoustic-to-Articulatory Inversion for Pronunciation Training","display_name":"Towards Acoustic-to-Articulatory Inversion for Pronunciation Training","publication_year":2023,"publication_date":"2023-08-18","ids":{"openalex":"https://openalex.org/W4385987299","doi":"https://doi.org/10.21437/slate.2023-14"},"language":"en","primary_location":{"id":"doi:10.21437/slate.2023-14","is_oa":false,"landing_page_url":"https://doi.org/10.21437/slate.2023-14","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"9th Workshop on Speech and Language Technology in Education (SLaTE)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.repository.cam.ac.uk/bitstreams/16f550a5-7af3-409f-8b55-b81aa8179eed/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104157969","display_name":"Charles G McGhee","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Charles G McGhee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032046290","display_name":"K.M. Knill","orcid":"https://orcid.org/0000-0003-1292-2769"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katherine M Knill","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Gales","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5104157969"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4956,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67647524,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"66","last_page":"70"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.970300018787384,"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"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.970300018787384,"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/pronunciation","display_name":"Pronunciation","score":0.868484616279602},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6678068041801453},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.6651406288146973},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5841152667999268},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.504034698009491},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.1620829701423645},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13792556524276733},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.04245424270629883},{"id":"https://openalex.org/keywords/seismology","display_name":"Seismology","score":0.04090806841850281}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.868484616279602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6678068041801453},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.6651406288146973},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5841152667999268},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.504034698009491},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.1620829701423645},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13792556524276733},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.04245424270629883},{"id":"https://openalex.org/C165205528","wikidata":"https://www.wikidata.org/wiki/Q83371","display_name":"Seismology","level":1,"score":0.04090806841850281},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C77928131","wikidata":"https://www.wikidata.org/wiki/Q193343","display_name":"Tectonics","level":2,"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":4,"locations":[{"id":"doi:10.21437/slate.2023-14","is_oa":false,"landing_page_url":"https://doi.org/10.21437/slate.2023-14","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"9th Workshop on Speech and Language Technology in Education (SLaTE)","raw_type":"proceedings-article"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/354290","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/354290","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/16f550a5-7af3-409f-8b55-b81aa8179eed/download","source":{"id":"https://openalex.org/S4306401776","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Object"},{"id":"pmh:doi:10.17863/cam.100150","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Object"},{"id":"doi:10.17863/cam.100150","is_oa":true,"landing_page_url":"https://doi.org/10.17863/cam.100150","pdf_url":null,"source":{"id":"https://openalex.org/S7407050737","display_name":"Apollo","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:www.repository.cam.ac.uk:1810/354290","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/354290","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/16f550a5-7af3-409f-8b55-b81aa8179eed/download","source":{"id":"https://openalex.org/S4306401776","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Object"},"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385987299.pdf","grobid_xml":"https://content.openalex.org/works/W4385987299.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2000075989","https://openalex.org/W4220683390","https://openalex.org/W2776838583"],"abstract_inverted_index":{"Visual":[0],"feedback":[1],"of":[2,14,64,86],"articulators":[3],"using":[4],"Electromagnetic-":[5],"Articulography":[6],"(EMA)":[7],"has":[8],"been":[9,68],"shown":[10,69],"to":[11,45,49,70,110],"aid":[12],"acquisition":[13],"non-native":[15],"speech":[16,47,56,65],"sounds.":[17],"Using":[18],"physical":[19],"EMA":[20,50],"sensors":[21],"is":[22],"expensive":[23],"and":[24,84,124],"invasive":[25],"making":[26],"it":[27],"impractical":[28],"for":[29,130],"providing":[30],"real-world":[31],"pronunciation":[32,131],"feedback.":[33],"Our":[34],"work":[35],"focuses":[36],"on":[37,74,106],"us-":[38],"ing":[39],"neural":[40],"Acoustic-to-Articulatory":[41],"Inversion":[42],"(AAI)":[43],"models":[44,88],"map":[46],"directly":[48],"sensor":[51],"positions.":[52],"Self-Supervised":[53],"Learning":[54],"(SSL)":[55],"models,":[57],"such":[58],"as":[59],"HuBERT,":[60],"can":[61],"produce":[62],"representations":[63,91],"that":[66,81,92,115],"have":[67,79],"significantly":[71],"improve":[72],"performance":[73],"AAI":[75,113],"tasks.":[76],"Probing":[77],"experiments":[78],"indicated":[80],"certain":[82],"layers":[83],"iterations":[85],"SSL":[87],"pro-":[89],"duce":[90],"may":[93],"yield":[94],"better":[95],"inversion":[96,122],"perfor-":[97],"mance":[98],"than":[99],"others.":[100],"In":[101],"this":[102],"paper,":[103],"we":[104],"build":[105],"these":[107],"probing":[108],"results":[109],"create":[111],"an":[112],"model":[114,123],"improves":[116],"upon":[117],"a":[118],"state-of-":[119],"the-art":[120],"baseline":[121],"evaluate":[125],"the":[126],"model\u2019s":[127],"suit-":[128],"ability":[129],"training.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}
