{"id":"https://openalex.org/W4415110493","doi":"https://doi.org/10.21437/interspeech.2025-1012","title":"Evaluating Logit-Based GOP Scores for Mispronunciation Detection","display_name":"Evaluating Logit-Based GOP Scores for Mispronunciation Detection","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415110493","doi":"https://doi.org/10.21437/interspeech.2025-1012"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-1012","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.12067","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119719074","display_name":"Aditya Kamlesh Parikh","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Aditya Kamlesh Parikh","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046936545","display_name":"Cristian Tejedor-Garc\u0131\u0301a","orcid":"https://orcid.org/0000-0001-5395-0438"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cristian Tejedor-Garcia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006678637","display_name":"Catia Cucchiarini","orcid":"https://orcid.org/0000-0001-5908-0824"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Catia Cucchiarini","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019585114","display_name":"Helmer Strik","orcid":"https://orcid.org/0000-0003-1722-3465"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Helmer Strik","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5119719074"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15726864,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2405","last_page":"2409"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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":0.9980000257492065,"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":0.9926000237464905,"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":0.9763000011444092,"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/pronunciation","display_name":"Pronunciation","score":0.7576000094413757},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6039000153541565},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.46389999985694885},{"id":"https://openalex.org/keywords/logit","display_name":"Logit","score":0.4401000142097473},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.43389999866485596},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.4278999865055084}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7576000094413757},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6291000247001648},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6039000153541565},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5867999792098999},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.46389999985694885},{"id":"https://openalex.org/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.4401000142097473},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.43389999866485596},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.4278999865055084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36239999532699585},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3479999899864197},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C51110983","wikidata":"https://www.wikidata.org/wiki/Q16503490","display_name":"Overconfidence effect","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26460000872612},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2533000111579895}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-1012","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.12067","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.12067","pdf_url":"https://arxiv.org/pdf/2506.12067","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.12067","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.12067","pdf_url":"https://arxiv.org/pdf/2506.12067","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Pronunciation":[0],"assessment":[1],"relies":[2],"on":[3,46,77],"goodness":[4],"of":[5,94],"pronunciation":[6,117],"(GOP)":[7],"scores,":[8],"traditionally":[9],"derived":[10],"from":[11,20],"softmax-based":[12],"posterior":[13,16],"probabilities.":[14],"However,":[15],"probabilities":[17],"may":[18],"suffer":[19],"overconfidence":[21],"and":[22,55,61,100,113],"poor":[23],"phoneme":[24],"separation,":[25],"limiting":[26],"their":[27,74],"effectiveness.":[28],"This":[29],"study":[30],"compares":[31],"logit-based":[32],"GOP":[33,37,70,83,96,108],"scores":[34,38,97],"with":[35,63,88],"probability-based":[36,69],"for":[39],"mispronunciation":[40],"detection.":[41],"We":[42],"conducted":[43],"our":[44],"experiment":[45],"two":[47],"L2":[48],"English":[49],"speech":[50],"datasets":[51],"spoken":[52],"by":[53],"Dutch":[54],"Mandarin":[56],"speakers,":[57],"assessing":[58],"classification":[59],"performance":[60],"correlation":[62],"human":[64,89],"ratings.":[65],"Logit-based":[66],"methods":[67,109],"outperform":[68],"in":[71],"classification,":[72],"but":[73],"effectiveness":[75],"depends":[76],"dataset":[78],"characteristics.":[79],"The":[80,103],"maximum":[81],"logit":[82,101],"shows":[84],"the":[85],"strongest":[86],"alignment":[87],"perception,":[90],"while":[91],"a":[92],"combination":[93],"different":[95],"balances":[98],"probability":[99],"features.":[102],"findings":[104],"suggest":[105],"that":[106],"hybrid":[107],"incorporating":[110],"uncertainty":[111],"modeling":[112],"phoneme-specific":[114],"weighting":[115],"improve":[116],"assessment.":[118]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-13T00:00:00"}