{"id":"https://openalex.org/W2054441760","doi":"https://doi.org/10.1109/iscslp.2010.5684845","title":"Capturing L2 segmental mispronunciations with joint-sequence models in Computer-Aided Pronunciation Training (CAPT)","display_name":"Capturing L2 segmental mispronunciations with joint-sequence models in Computer-Aided Pronunciation Training (CAPT)","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W2054441760","doi":"https://doi.org/10.1109/iscslp.2010.5684845","mag":"2054441760"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2010.5684845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language Processing","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/A5101881032","display_name":"Xiaojun Qian","orcid":"https://orcid.org/0000-0002-6026-8928"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK","US"],"is_corresponding":true,"raw_author_name":"Xiaojun Qian","raw_affiliation_strings":["CUHK MoE-Microsoft, Key Laboratory of Human-Centric Computing and Interface Technologies, Hong Kong, China","CUHK MoE-Microsoft Key Laboratory of Human-Centric Computing and Interface Technologies, China"],"affiliations":[{"raw_affiliation_string":"CUHK MoE-Microsoft, Key Laboratory of Human-Centric Computing and Interface Technologies, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"CUHK MoE-Microsoft Key Laboratory of Human-Centric Computing and Interface Technologies, China","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["Department of SEEM, Chinese University of Hong Kong, Hong Kong, China","Department of SEEM, The Chinese University of Hong Kong, Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"Department of SEEM, Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of SEEM, The Chinese University of Hong Kong, Hong Kong SAR","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Frank Soong","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","[Speech Group, Microsoft Research Asia, Beijing, China]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Speech Group, Microsoft Research Asia, Beijing, China]","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101881032"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":2.7929,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.91087217,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"84","last_page":"88"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9990000128746033,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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":0.8316701650619507},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.798054039478302},{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.6877645254135132},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5721672773361206},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5672236680984497},{"id":"https://openalex.org/keywords/phonetic-transcription","display_name":"Phonetic transcription","score":0.5610048174858093},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5581936240196228},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5504079461097717},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5393085479736328},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.524589478969574},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41966187953948975},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14598402380943298},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07690837979316711}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8316701650619507},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.798054039478302},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.6877645254135132},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5721672773361206},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5672236680984497},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.5610048174858093},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5581936240196228},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5504079461097717},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5393085479736328},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.524589478969574},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41966187953948975},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14598402380943298},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07690837979316711},{"id":"https://openalex.org/C42360764","wikidata":"https://www.wikidata.org/wiki/Q83588","display_name":"Chemical engineering","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iscslp.2010.5684845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.309.2087","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.309.2087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www1.se.cuhk.edu.hk/~hccl/publications/pub/xiaojun_iscslp2010.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W225859850","https://openalex.org/W275138538","https://openalex.org/W290344559","https://openalex.org/W296713244","https://openalex.org/W1496430420","https://openalex.org/W1582482241","https://openalex.org/W2002342963","https://openalex.org/W2008834750","https://openalex.org/W2090755665","https://openalex.org/W2137268753","https://openalex.org/W2137469438","https://openalex.org/W2139008940","https://openalex.org/W2160783805","https://openalex.org/W2400818677","https://openalex.org/W4390912567","https://openalex.org/W6859979365"],"related_works":["https://openalex.org/W2621258238","https://openalex.org/W2080578089","https://openalex.org/W3114261385","https://openalex.org/W2917843404","https://openalex.org/W2161573742","https://openalex.org/W2462492290","https://openalex.org/W2008308193","https://openalex.org/W3037190132","https://openalex.org/W2179005426","https://openalex.org/W2153997805"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3],"present":[4],"an":[5],"extension":[6],"to":[7,47,52],"our":[8],"previous":[9,60],"efforts":[10],"on":[11,66],"automatically":[12],"detecting":[13],"text-dependent":[14],"segmental":[15,33],"mispronunciations":[16,82],"by":[17,38],"Cantonese":[18],"(L1)":[19],"learners":[20],"of":[21,32,58,62],"American":[22],"English":[23],"(L2),":[24],"through":[25],"modeling":[26,35],"the":[27,49,59,70,77,81,85],"L2":[28],"production.":[29],"The":[30],"problem":[31],"mispronunciation":[34],"is":[36,45],"addressed":[37],"joint-sequence":[39],"models.":[40],"Specifically,":[41],"a":[42,67],"grapheme-to-phoneme":[43],"model":[44],"built":[46],"convert":[48],"prompted":[50],"words":[51],"their":[53],"corresponding":[54],"possible":[55],"mispronunciations,":[56],"instead":[57],"characterization":[61],"phonological":[63,90],"processes":[64],"based":[65,87],"transfer":[68],"from":[69],"canonical":[71],"phonetic":[72],"transcription.":[73],"Experiments":[74],"show":[75],"that":[76],"approach":[78],"can":[79],"capture":[80],"better":[83],"than":[84],"knowledge":[86],"and":[88],"data-driven":[89],"rules.":[91]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}