{"id":"https://openalex.org/W4385823283","doi":"https://doi.org/10.21437/interspeech.2023-2371","title":"Assessment of Non-Native Speech Intelligibility using Wav2vec2-based Mispronunciation Detection and Multi-level Goodness of Pronunciation Transformer","display_name":"Assessment of Non-Native Speech Intelligibility using Wav2vec2-based Mispronunciation Detection and Multi-level Goodness of Pronunciation Transformer","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823283","doi":"https://doi.org/10.21437/interspeech.2023-2371"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-2371","doi":"https://doi.org/10.21437/interspeech.2023-2371","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2371","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 2023","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5002916261","display_name":"Ram C. M. C. Shekar","orcid":"https://orcid.org/0009-0003-5282-3551","observed_orcids":["https://orcid.org/0009-0003-5282-3551"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ram C. M. C. Shekar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100542450","display_name":"Yang Mu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mu Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kevin Hirschi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stephen Looney","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Okim Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"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":[],"countries":[],"is_corresponding":false,"raw_author_name":"John H. L. Hansen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5326,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.63571257,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"984","last_page":"988"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.989300012588501,"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":0.989300012588501,"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":0.005499999970197678,"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":0.002899999963119626,"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/non-native-speech","display_name":"non-native speech","score":0.9520000219345093},{"id":"https://openalex.org/keywords/speech-intelligibility","display_name":"speech intelligibility","score":0.9559999704360962},{"id":"https://openalex.org/keywords/mispronunciation-detection","display_name":"mispronunciation detection","score":0.9929999709129333},{"id":"https://openalex.org/keywords/wav2vec-2-0","display_name":"wav2vec 2.0","score":0.878000020980835},{"id":"https://openalex.org/keywords/pronunciation-assessment","display_name":"pronunciation assessment","score":0.5789999961853027},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.3149999976158142}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7140611410140991},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.63411945104599},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5903092622756958},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5699889063835144},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5553075671195984},{"id":"https://openalex.org/C132480984","wikidata":"https://www.wikidata.org/wiki/Q2034239","display_name":"Goodness of fit","level":2,"score":0.4377361834049225},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3506990671157837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32631754875183105},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18352988362312317},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09883186221122742},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.06088951230049133},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-2371","doi":"https://doi.org/10.21437/interspeech.2023-2371","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2371","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 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3198712976","https://openalex.org/W3197816268","https://openalex.org/W3197474936","https://openalex.org/W4402111464","https://openalex.org/W3196525293","https://openalex.org/W4385822982","https://openalex.org/W4385977645","https://openalex.org/W178457378","https://openalex.org/W2405229007","https://openalex.org/W205236327"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-13T10:08:12.033832","created_date":"2023-08-15T00:00:00"}
