{"id":"https://openalex.org/W4297841533","doi":"https://doi.org/10.21437/interspeech.2022-11039","title":"Improving Mispronunciation Detection with Wav2vec2-based Momentum Pseudo-Labeling for Accentedness and Intelligibility Assessment","display_name":"Improving Mispronunciation Detection with Wav2vec2-based Momentum Pseudo-Labeling for Accentedness and Intelligibility Assessment","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841533","doi":"https://doi.org/10.21437/interspeech.2022-11039"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11039","doi":"https://doi.org/10.21437/interspeech.2022-11039","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11039","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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":"Interspeech 2022","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.15937","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100542450","display_name":"Yang Mu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mu Yang","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050069117","display_name":"Kevin Hirschi","orcid":"https://orcid.org/0000-0002-0838-3494","observed_orcids":["https://orcid.org/0000-0002-0838-3494"]},"institutions":[{"id":"https://openalex.org/I203172682","display_name":"Northern Arizona University","ror":"https://ror.org/0272j5188","country_code":"US","type":"education","lineage":["https://openalex.org/I203172682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Hirschi","raw_affiliation_strings":["Northern Arizona University, Flagstaff, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northern Arizona University, Flagstaff, AZ, USA","institution_ids":["https://openalex.org/I203172682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013317158","display_name":"Stephen Daniel Looney","orcid":"https://orcid.org/0000-0001-9968-7276","observed_orcids":["https://orcid.org/0000-0001-9968-7276"]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen Daniel Looney","raw_affiliation_strings":["Pennsylvania State University, State College, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, State College, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019197893","display_name":"Okim Kang","orcid":"https://orcid.org/0000-0002-7721-5283","observed_orcids":["https://orcid.org/0000-0002-7721-5283"]},"institutions":[{"id":"https://openalex.org/I203172682","display_name":"Northern Arizona University","ror":"https://ror.org/0272j5188","country_code":"US","type":"education","lineage":["https://openalex.org/I203172682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Okim Kang","raw_affiliation_strings":["Northern Arizona University, Flagstaff, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northern Arizona University, Flagstaff, AZ, USA","institution_ids":["https://openalex.org/I203172682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H.L. Hansen","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2441,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.82788633,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4481","last_page":"4485"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9878000020980835,"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":0.9878000020980835,"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":0.007400000002235174,"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":0.0020000000949949026,"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/pseudo-labeling","display_name":"pseudo-labeling","score":0.8949999809265137},{"id":"https://openalex.org/keywords/wav2vec-2-0","display_name":"wav2vec 2.0","score":0.8619999885559082},{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.8610000014305115},{"id":"https://openalex.org/keywords/second-language-speech","display_name":"second language speech","score":0.8519999980926514},{"id":"https://openalex.org/keywords/phoneme-recognition","display_name":"phoneme recognition","score":0.7870000004768372},{"id":"https://openalex.org/keywords/speech-intelligibility","display_name":"speech intelligibility","score":0.8339999914169312},{"id":"https://openalex.org/keywords/unlabeled-data","display_name":"unlabeled data","score":0.5299999713897705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5695968866348267},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5611650347709656},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48212695121765137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33863991498947144},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06705713272094727},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2022-11039","doi":"https://doi.org/10.21437/interspeech.2022-11039","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11039","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2203.15937","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.15937","pdf_url":"https://arxiv.org/pdf/2203.15937","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2203.15937","doi":"https://doi.org/10.48550/arxiv.2203.15937","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2203.15937","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2203.15937","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.15937","pdf_url":"https://arxiv.org/pdf/2203.15937","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310831","display_name":"Northern Arizona University","ror":"https://ror.org/0272j5188"},{"id":"https://openalex.org/F4320327708","display_name":"University of Texas at Dallas","ror":"https://ror.org/049emcs32"},{"id":"https://openalex.org/F4320332169","display_name":"Directorate for Computer and Information Science and Engineering","ror":"https://ror.org/025kzpk63"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4297841533.pdf","grobid_xml":"https://content.openalex.org/works/W4297841533.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2091856355","https://openalex.org/W2401896499","https://openalex.org/W2407080277","https://openalex.org/W2552635739","https://openalex.org/W2888954148","https://openalex.org/W2889488531","https://openalex.org/W2896457183","https://openalex.org/W2972347929","https://openalex.org/W2979826702","https://openalex.org/W3015231007","https://openalex.org/W3015522062","https://openalex.org/W3017961061","https://openalex.org/W3026041220","https://openalex.org/W3036601975","https://openalex.org/W3095953768","https://openalex.org/W3096338464","https://openalex.org/W3097515180","https://openalex.org/W3097911750","https://openalex.org/W3114586309","https://openalex.org/W3160525311","https://openalex.org/W3167533889","https://openalex.org/W3169320628","https://openalex.org/W3196525293","https://openalex.org/W3197816268","https://openalex.org/W3198712976","https://openalex.org/W3200030979","https://openalex.org/W3207925072","https://openalex.org/W3209984917","https://openalex.org/W4286905321","https://openalex.org/W4287118210","https://openalex.org/W4287374065","https://openalex.org/W4287553982"],"related_works":["https://openalex.org/W4410642990","https://openalex.org/W3205351443","https://openalex.org/W4405709756","https://openalex.org/W7133234393","https://openalex.org/W3097515180","https://openalex.org/W4401070329","https://openalex.org/W4392904020","https://openalex.org/W3198712976","https://openalex.org/W7165666785","https://openalex.org/W4408353580"],"abstract_inverted_index":{"Current":[0],"leading":[1],"mispronunciation":[2],"detection":[3],"and":[4,44,65,86,122,159,191],"diagnosis":[5],"(MDD)":[6],"systems":[7],"achieve":[8],"promising":[9],"performance":[10],"via":[11,39],"end-to-end":[12,19],"phoneme":[13,118],"recognition.":[14],"One":[15],"challenge":[16],"of":[17,24,92],"such":[18],"solutions":[20],"is":[21,102,137],"the":[22,46,75,93,148],"scarcity":[23],"human-annotated":[25],"phonemes":[26],"on":[27,50,171,189],"natural":[28],"L2":[29,37,71,78],"speech.":[30],"In":[31,164],"this":[32],"work,":[33],"we":[34,57,166],"leverage":[35],"unlabeled":[36],"speech":[38,72,79],"a":[40,116,129,156,172,182],"pseudo-labeling":[41],"(PL)":[42],"procedure":[43],"extend":[45],"fine-tuning":[47,111,131],"approach":[48],"based":[49,188],"pre-trained":[51],"self-supervised":[52],"learning":[53],"(SSL)":[54],"models.":[55],"Specifically,":[56],"use":[58],"Wav2vec":[59],"2.0":[60],"as":[61],"our":[62,100,152,177],"SSL":[63],"model,":[64],"fine-tune":[66],"it":[67],"using":[68],"original":[69],"labeled":[70],"samples":[73],"plus":[74],"created":[76],"pseudo-labeled":[77],"samples.":[80],"Our":[81],"pseudo":[82,105,113],"labels":[83,114],"are":[84,87],"dynamic":[85],"produced":[88],"by":[89],"an":[90,168],"ensemble":[91],"online":[94],"model":[95,101],"on-the-fly,":[96],"which":[97],"ensures":[98],"that":[99,110],"robust":[103],"to":[104,140,147],"label":[106],"noise.":[107],"We":[108],"show":[109,181],"with":[112,185],"achieves":[115],"5.35%":[117],"error":[119,162],"rate":[120],"reduction":[121],"2.48%":[123],"MDD":[124,150,153],"F1":[125],"score":[126],"improvement":[127],"over":[128],"labeled-samples-only":[130],"baseline.":[132],"The":[133],"proposed":[134],"PL":[135,144],"method":[136],"also":[138],"shown":[139],"outperform":[141],"conventional":[142],"offline":[143],"methods.":[145],"Compared":[146],"state-of-the-art":[149],"systems,":[151],"solution":[154],"produces":[155],"more":[157],"accurate":[158],"consistent":[160],"phonetic":[161],"diagnosis.":[163],"addition,":[165],"conduct":[167],"open":[169],"test":[170],"separate":[173],"UTD-4Accents":[174],"dataset,":[175],"where":[176],"system":[178],"recognition":[179],"outputs":[180],"strong":[183],"correlation":[184],"human":[186],"perception,":[187],"accentedness":[190],"intelligibility.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2022-10-01T00:00:00"}