{"id":"https://openalex.org/W4416798423","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249038","title":"Multi-Task Pretraining for Enhancing Interpretable L2 Pronunciation Assessment","display_name":"Multi-Task Pretraining for Enhancing Interpretable L2 Pronunciation Assessment","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798423","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249038"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249038","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5035426420","display_name":"Jiun-Ting Li","orcid":null},"institutions":[{"id":"https://openalex.org/I92172085","display_name":"Chunghwa Telecom (Taiwan)","ror":"https://ror.org/04f786589","country_code":"TW","type":"company","lineage":["https://openalex.org/I92172085"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jiun-Ting Li","raw_affiliation_strings":["Chunghwa Telecom Co., Ltd.,Advanced Technology Laboratory,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chunghwa Telecom Co., Ltd.,Advanced Technology Laboratory,Taiwan","institution_ids":["https://openalex.org/I92172085"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061406456","display_name":"Bi-Cheng Yan","orcid":"https://orcid.org/0009-0002-1987-2418"},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Bi-Cheng Yan","raw_affiliation_strings":["National Taiwan Normal University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100411058","display_name":"Yicheng Wang","orcid":"https://orcid.org/0009-0004-5670-0054"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Cheng Wang","raw_affiliation_strings":["National Taiwan University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020074097","display_name":"Berlin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Berlin Chen","raw_affiliation_strings":["National Taiwan Normal University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Taiwan","institution_ids":["https://openalex.org/I134161618"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17625222,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"531","last_page":"536"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.4560999870300293,"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":0.4560999870300293,"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":0.3325999975204468,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.04149999842047691,"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":0.9337999820709229},{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.5392000079154968},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5182999968528748},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4805999994277954},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.34689998626708984},{"id":"https://openalex.org/keywords/language-proficiency","display_name":"Language proficiency","score":0.34459999203681946},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.32679998874664307}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.9337999820709229},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.555899977684021},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.5392000079154968},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5182999968528748},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4805999994277954},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46000000834465027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4413999915122986},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41670000553131104},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.40790000557899475},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.36800000071525574},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C2778883600","wikidata":"https://www.wikidata.org/wiki/Q2390977","display_name":"Language proficiency","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C43122875","wikidata":"https://www.wikidata.org/wiki/Q5428522","display_name":"Facet (psychology)","level":4,"score":0.26829999685287476},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C21036866","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249038","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":32,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2118774185","https://openalex.org/W2130200371","https://openalex.org/W2135046866","https://openalex.org/W2145604446","https://openalex.org/W2191779130","https://openalex.org/W2291393697","https://openalex.org/W2575689684","https://openalex.org/W2963341956","https://openalex.org/W2972382531","https://openalex.org/W2972799030","https://openalex.org/W3042708701","https://openalex.org/W3123665557","https://openalex.org/W3197324626","https://openalex.org/W3197742413","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4211169222","https://openalex.org/W4224928163","https://openalex.org/W4312069033","https://openalex.org/W4319862255","https://openalex.org/W4372262414","https://openalex.org/W4375850654","https://openalex.org/W4385822636","https://openalex.org/W4385823091","https://openalex.org/W4385823466","https://openalex.org/W4389518865","https://openalex.org/W4391021541","https://openalex.org/W4402112180","https://openalex.org/W4406461643","https://openalex.org/W4408352933","https://openalex.org/W4412886823"],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"pronunciation":[1,12,31,40,60,65,89,122,133,197],"assessment":[2,144],"(APA)":[3],"analyzes":[4],"second-language":[5],"(L2)":[6],"learners'":[7],"speech":[8],"by":[9,164],"providing":[10],"fine-grained":[11],"feedback":[13],"at":[14,33],"various":[15],"linguistic":[16,48],"levels.":[17],"Most":[18],"existing":[19],"efforts":[20],"on":[21,58,130,151,193],"APA":[22,113,137],"typically":[23],"adopt":[24],"segmental-level":[25,121],"features":[26,123,167],"as":[27,170],"inputs":[28],"and":[29,53,124,154,176,199,206],"predict":[30],"scores":[32],"different":[34],"granularities":[35],"via":[36,99,185],"hierarchical":[37],"(or":[38],"parallel)":[39],"modeling.":[41],"This,":[42],"however,":[43],"inevitably":[44],"causes":[45],"assessments":[46],"across":[47],"levels":[49],"(e.g.,":[50],"phone,":[51],"word,":[52],"utterance)":[54],"to":[55,85,187],"rely":[56],"solely":[57],"phoneme-level":[59,109],"features,":[61],"nearly":[62],"sidelining":[63],"supra-segmental":[64],"cues.":[66],"To":[67],"address":[68],"this":[69,162],"limitation,":[70],"we":[71],"introduce":[72],"multi-task":[73],"pretraining":[74],"(MTP)":[75],"for":[76,107],"APA,":[77],"a":[78,108],"simple":[79],"yet":[80],"effective":[81],"strategy":[82,118],"that":[83],"attempts":[84],"capture":[86],"long-term":[87],"temporal":[88],"cues":[90],"while":[91],"strengthening":[92],"the":[93,100,115,126],"intrinsic":[94],"structures":[95],"within":[96],"an":[97,112],"utterance":[98],"objective":[101],"of":[102,111],"reconstructing":[103],"input":[104],"features.":[105],"Specifically,":[106],"encoder":[110],"model,":[114],"proposed":[116],"MTP":[117],"randomly":[119],"masks":[120],"reconstructs":[125],"masked":[127],"ones":[128],"based":[129],"their":[131],"surrounding":[132],"context.":[134],"Furthermore,":[135],"current":[136],"systems":[138],"lack":[139],"integration":[140],"with":[141],"automated":[142],"speaking":[143],"(ASA),":[145],"limiting":[146],"holistic":[147],"proficiency":[148,190,201,208],"evaluation.":[149],"Drawing":[150],"empirical":[152],"studies":[153],"prior":[155],"knowledge":[156],"in":[157],"ASA,":[158],"our":[159],"framework":[160],"bridges":[161],"gap":[163],"incorporating":[165],"handcrafted":[166],"(HCFs),":[168],"such":[169],"fluency":[171],"(speech":[172],"rate,":[173],"silence":[174],"duration)":[175],"stress":[177],"(pitch":[178],"accent":[179],"strength),":[180],"derived":[181],"from":[182],"human-designed":[183],"formulas":[184],"regressors":[186],"generate":[188],"interpretable":[189],"scores.":[191],"Experiments":[192],"speechocean762":[194],"show":[195],"improved":[196],"scoring":[198],"ASA":[200],"correlation,":[202],"enabling":[203],"targeted":[204],"training":[205],"comprehensive":[207],"assessment.":[209]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}
