{"id":"https://openalex.org/W4417072987","doi":"https://doi.org/10.1145/3743093.3771002","title":"Phoneme-Controlled LLM with Self-Supervised Speech Prompts for Mispronunciation Detection","display_name":"Phoneme-Controlled LLM with Self-Supervised Speech Prompts for Mispronunciation Detection","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4417072987","doi":"https://doi.org/10.1145/3743093.3771002"},"language":null,"primary_location":{"id":"doi:10.1145/3743093.3771002","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3771002","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771002","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771002","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112113739","display_name":"Zhengping Song","orcid":"https://orcid.org/0009-0006-7714-5330"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhengping Song","raw_affiliation_strings":["Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0009-0006-7714-5330","affiliations":[{"raw_affiliation_string":"Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061296090","display_name":"Zaokere Kadeer","orcid":"https://orcid.org/0000-0001-9475-1101"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zaokere Kadeer","raw_affiliation_strings":["Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0001-9475-1101","affiliations":[{"raw_affiliation_string":"Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120692652","display_name":"Mulati Kahaer","orcid":"https://orcid.org/0009-0002-0973-4505"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mulati Kahaer","raw_affiliation_strings":["Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0009-0002-0973-4505","affiliations":[{"raw_affiliation_string":"Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051018181","display_name":"Xingsheng Pang","orcid":"https://orcid.org/0009-0001-3562-2876"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"XuDong Pang","raw_affiliation_strings":["Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0009-0001-3562-2876","affiliations":[{"raw_affiliation_string":"Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062830446","display_name":"Yinfeng Yu","orcid":"https://orcid.org/0000-0003-3089-4140"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinfeng Yu","raw_affiliation_strings":["Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0003-3089-4140","affiliations":[{"raw_affiliation_string":"Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077794475","display_name":"Aishan Wumaier","orcid":"https://orcid.org/0000-0003-1681-1089"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aishan Wumaier","raw_affiliation_strings":["Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0003-1681-1089","affiliations":[{"raw_affiliation_string":"Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5112113739"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19854334,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8348000049591064,"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":0.8348000049591064,"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/T10863","display_name":"Voice and Speech Disorders","score":0.04560000076889992,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.029200000688433647,"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":0.8098999857902527},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5059999823570251},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4796999990940094},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.4729999899864197},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45739999413490295},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.44909998774528503},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4438999891281128},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4187999963760376}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8213000297546387},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8098999857902527},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6097999811172485},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5892000198364258},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5059999823570251},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.489300012588501},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4796999990940094},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.4729999899864197},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45739999413490295},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.44909998774528503},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4438999891281128},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4187999963760376},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.40540000796318054},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26420000195503235},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.257999986410141}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3743093.3771002","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3771002","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771002","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3743093.3771002","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3771002","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771002","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417072987.pdf","grobid_xml":"https://content.openalex.org/works/W4417072987.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1635512741","https://openalex.org/W1769175087","https://openalex.org/W1985084205","https://openalex.org/W2091856355","https://openalex.org/W2127141656","https://openalex.org/W2139008940","https://openalex.org/W2402640444","https://openalex.org/W2406502879","https://openalex.org/W2768986418","https://openalex.org/W2888954148","https://openalex.org/W2890915139","https://openalex.org/W2938359332","https://openalex.org/W3013336802","https://openalex.org/W3015231007","https://openalex.org/W3134482008","https://openalex.org/W3197816268","https://openalex.org/W4225324745","https://openalex.org/W4320009770","https://openalex.org/W4388672923","https://openalex.org/W4392903956","https://openalex.org/W4401587020"],"related_works":[],"abstract_inverted_index":{"Pronunciation":[0,12],"Error":[1],"Detection":[2],"and":[3,15,61,63,81,114,131,133,140],"Diagnosis":[4],"(MDD)":[5],"is":[6],"a":[7,35,52,82,105,115],"key":[8],"technology":[9],"in":[10,29],"Computer-Assisted":[11,16],"Training":[13],"(CAPT)":[14],"Language":[17],"Learning":[18],"(CALL).":[19],"Recently":[20],"large":[21,64],"language":[22,65,90],"models":[23,66],"(LLMs)":[24],"have":[25],"shown":[26],"strong":[27],"performance":[28],"multimodal":[30,71],"tasks.":[31],"This":[32],"paper":[33],"proposes":[34],"new":[36],"MDD":[37],"framework":[38],"called":[39],"S-TATLLM":[40,103],"which":[41,121],"combines":[42],"the":[43,86,89,125,134],"advantages":[44],"of":[45,107,112,119],"an":[46,69,109],"incremental":[47],"self-supervised":[48],"model":[49,91],"(based":[50],"on":[51,94],"local-global":[53],"feature":[54],"extraction":[55],"structure":[56],"CGSL":[57],"using":[58],"multi-head":[59],"self-attention":[60],"convolution)":[62],"to":[67,92],"build":[68],"end-to-end":[70],"pronunciation":[72,97],"error":[73],"detection":[74,101],"system.":[75],"By":[76],"introducing":[77],"phoneme-level":[78],"control":[79],"information":[80],"text-audio-text":[83],"embedding":[84],"approach":[85],"system":[87],"guides":[88],"focus":[93],"easily":[95],"confused":[96],"errors":[98],"thus":[99],"improving":[100],"performance.":[102],"achieves":[104],"recall":[106],"99.44%":[108],"F1":[110],"score":[111],"0.8281":[113],"diagnosis":[116],"accuracy":[117],"(DER)":[118],"92.03%":[120],"are":[122],"better":[123],"than":[124],"wav2vec2-CTC":[126],"method":[127,136],"with":[128,137],"60.84%":[129],"0.6164":[130],"70.74%":[132],"AEL":[135],"73.71%":[138],"0.7749":[139],"81.60%.":[141]},"counts_by_year":[],"updated_date":"2026-03-08T06:56:09.383167","created_date":"2025-12-06T00:00:00"}