{"id":"https://openalex.org/W4415524401","doi":"https://doi.org/10.1109/mlsp62443.2025.11204310","title":"Automated Pronunciation Scoring of Child L2 Learners with Score Calibration for Imbalanced Distributions","display_name":"Automated Pronunciation Scoring of Child L2 Learners with Score Calibration for Imbalanced Distributions","publication_year":2025,"publication_date":"2025-08-31","ids":{"openalex":"https://openalex.org/W4415524401","doi":"https://doi.org/10.1109/mlsp62443.2025.11204310"},"language":null,"primary_location":{"id":"doi:10.1109/mlsp62443.2025.11204310","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5022767796","display_name":"Yuuki Tachioka","orcid":"https://orcid.org/0009-0002-0587-2943"},"institutions":[{"id":"https://openalex.org/I4210132650","display_name":"Denso (Japan)","ror":"https://ror.org/04hkpfa76","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210132650"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuuki Tachioka","raw_affiliation_strings":["Denso IT Laboratory,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Denso IT Laboratory,Tokyo,Japan","institution_ids":["https://openalex.org/I4210132650"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5022767796"],"corresponding_institution_ids":["https://openalex.org/I4210132650"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32068519,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9695000052452087,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9695000052452087,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9524999856948853,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9142000079154968,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6444000005722046},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.5986999869346619},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5824000239372253},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.489300012588501},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4779999852180481},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.4242999851703644},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.41370001435279846},{"id":"https://openalex.org/keywords/standard-score","display_name":"Standard score","score":0.40849998593330383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6503999829292297},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6444000005722046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6164000034332275},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.5986999869346619},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5824000239372253},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.489300012588501},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4779999852180481},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46639999747276306},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.4242999851703644},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.41370001435279846},{"id":"https://openalex.org/C20256973","wikidata":"https://www.wikidata.org/wiki/Q1050272","display_name":"Standard score","level":2,"score":0.40849998593330383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38339999318122864},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.3815000057220459},{"id":"https://openalex.org/C2778883600","wikidata":"https://www.wikidata.org/wiki/Q2390977","display_name":"Language proficiency","level":2,"score":0.3677999973297119},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.3621000051498413},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.30399999022483826},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C173633133","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw score","level":3,"score":0.28209999203681946},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2766999900341034},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp62443.2025.11204310","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W612558043","https://openalex.org/W2295598076","https://openalex.org/W3042014356","https://openalex.org/W3145048926","https://openalex.org/W3202278141","https://openalex.org/W4226396022","https://openalex.org/W4317419706","https://openalex.org/W4385731991","https://openalex.org/W4385987567","https://openalex.org/W4389518865","https://openalex.org/W4390653881","https://openalex.org/W4406461503","https://openalex.org/W4407256759"],"related_works":[],"abstract_inverted_index":{"Automated":[0],"pronunciation":[1],"assessment":[2],"for":[3,141,167],"children":[4],"learning":[5],"the":[6,15,41,49,62,72,77,87,92,116,120,127,136,148,164,168],"second":[7],"language":[8,172],"(L2)":[9],"is":[10,52,95,151],"challenging":[11],"and":[12,32,109],"important.":[13],"For":[14],"Nonnative":[16],"Children's":[17],"Automatic":[18],"Speech":[19],"Assessment":[20],"(NOCASA)":[21],"challenge,":[22,47],"we":[23,98],"developed":[24],"a":[25,36,46,65,106,158],"system":[26],"that":[27],"predicts":[28],"both":[29],"word":[30],"content":[31],"proficiency":[33,90,162],"scores":[34,101,104,117],"using":[35,105],"multitask":[37],"wav2vec2":[38,81],"model.":[39],"However,":[40],"imbalanced":[42],"score":[43,74,122,139,166],"distribution":[44,75],"presents":[45],"as":[48],"primary":[50],"metric":[51],"Unweighted":[53],"Average":[54],"Recall":[55],"(UAR),":[56],"which":[57],"requires":[58],"careful":[59],"handling":[60],"of":[61,68,138,147],"class":[63,94],"with":[64],"small":[66,159],"number":[67],"samples.":[69],"To":[70],"fit":[71,119],"original":[73],"to":[76,114,118,152],"reference":[78,121],"ones,":[79],"discrete":[80],"outputs":[82],"cannot":[83],"be":[84],"used":[85],"because":[86],"difference":[88],"in":[89,133,161],"within":[91,163],"same":[93,165],"ignored.":[96],"Thus,":[97],"first":[99],"convert":[100],"into":[102],"continuous":[103],"regression":[107],"model":[108],"then":[110],"use":[111],"three":[112],"methods":[113],"calibrate":[115],"distribution.":[123],"Our":[124],"experiments":[125],"on":[126],"NOCASA":[128],"challenge":[129],"show":[130],"significant":[131],"improvements":[132],"UAR,":[134],"highlighting":[135],"importance":[137],"calibration":[140],"precise":[142],"automated":[143],"assessment.":[144],"Another":[145],"advantage":[146],"proposed":[149],"method":[150],"provide":[153],"more":[154],"accurate":[155],"feedback,":[156],"including":[157],"improvement":[160],"children,":[169],"encouraging":[170],"their":[171],"development.":[173]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}