{"id":"https://openalex.org/W3012448349","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023156","title":"A Study on Mispronunciation Detection Based on Fine-grained Speech Attribute","display_name":"A Study on Mispronunciation Detection Based on Fine-grained Speech Attribute","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3012448349","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023156","mag":"3012448349"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5075041615","display_name":"Minghao Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghao Guo","raw_affiliation_strings":["Beijing Advanced Innovation Center for Language Resources, Beijing Language and Culture University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Advanced Innovation Center for Language Resources, Beijing Language and Culture University, Beijing, China","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cai Rui","orcid":null},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cai Rui","raw_affiliation_strings":["Beijing Advanced Innovation Center for Language Resources, Beijing Language and Culture University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Advanced Innovation Center for Language Resources, Beijing Language and Culture University, Beijing, China","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392089","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-8180-2886"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Beijing Advanced Innovation Center for Language Resources, Beijing Language and Culture University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Advanced Innovation Center for Language Resources, Beijing Language and Culture University, Beijing, China","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101084840","display_name":"Binghuai Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binghuai Lin","raw_affiliation_strings":["MIG, Tencent Science and Technology Ltd., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIG, Tencent Science and Technology Ltd., Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052176517","display_name":"Jinsong Zhang","orcid":"https://orcid.org/0000-0002-1603-3136"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinsong Zhang","raw_affiliation_strings":["Beijing Advanced Innovation Center for Language Resources, Beijing Language and Culture University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Advanced Innovation Center for Language Resources, Beijing Language and Culture University, Beijing, China","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006684220","display_name":"Yanlu Xie","orcid":"https://orcid.org/0000-0001-6765-4808"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanlu Xie","raw_affiliation_strings":["Beijing Advanced Innovation Center for Language Resources, Beijing Language and Culture University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Advanced Innovation Center for Language Resources, Beijing Language and Culture University, Beijing, China","institution_ids":["https://openalex.org/I115212828"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.21090722,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"2019","issue":null,"first_page":"1197","last_page":"1201"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9916999936103821,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9865999817848206,"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/computer-science","display_name":"Computer science","score":0.8329851627349854},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7975127696990967},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6779274940490723},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5725400447845459},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49950242042541504},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4933864176273346},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44022059440612793},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4374111294746399},{"id":"https://openalex.org/keywords/phonetics","display_name":"Phonetics","score":0.42166927456855774},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08920344710350037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8329851627349854},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7975127696990967},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6779274940490723},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5725400447845459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49950242042541504},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4933864176273346},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44022059440612793},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4374111294746399},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.42166927456855774},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08920344710350037},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},{"id":"mag:3045673822","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002266604977600","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W7155391","https://openalex.org/W103312509","https://openalex.org/W1505035441","https://openalex.org/W1944979302","https://openalex.org/W1980850109","https://openalex.org/W1999488431","https://openalex.org/W2010548701","https://openalex.org/W2049905800","https://openalex.org/W2060630096","https://openalex.org/W2067093722","https://openalex.org/W2091856355","https://openalex.org/W2116648050","https://openalex.org/W2132534451","https://openalex.org/W2150769028","https://openalex.org/W2165436104","https://openalex.org/W2397987315","https://openalex.org/W2398529454","https://openalex.org/W2401896499","https://openalex.org/W2403033074","https://openalex.org/W2663878505","https://openalex.org/W2668277942","https://openalex.org/W2749848124","https://openalex.org/W2952387069","https://openalex.org/W4245838404","https://openalex.org/W4301037946","https://openalex.org/W6600298696","https://openalex.org/W6712710612","https://openalex.org/W6713505222","https://openalex.org/W6764704314"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2000075989","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W1607396156","https://openalex.org/W2381961785","https://openalex.org/W4313330181","https://openalex.org/W2342291550"],"abstract_inverted_index":{"Over":[0],"the":[1,65,115,119,136,149],"last":[2],"decade,":[3],"several":[4],"studies":[5],"have":[6],"investigated":[7],"speech":[8,22,48,58,88,144],"attribute":[9,23,49,59,89],"detection":[10,122],"(SAD)":[11],"for":[12],"improving":[13],"computer":[14],"assisted":[15],"pronunciation":[16],"training":[17],"(CAPT)":[18],"systems.":[19],"The":[20],"predefined":[21],"categories":[24],"either":[25],"is":[26,33,109,138],"IPA":[27],"or":[28],"language":[29],"dependent":[30],"categories,":[31],"which":[32,53,157],"difficult":[34],"to":[35,80,128],"handle":[36],"multiple":[37],"languages":[38],"mispronunciation":[39,121],"detection.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44,146],"propose":[45],"a":[46,73,124],"fine-grained":[47],"(FSA)":[50],"modeling":[51,142],"method,":[52],"defines":[54],"types":[55],"of":[56,118,130,141],"Chinese":[57,62,76,106],"by":[60],"combining":[61],"phonetics":[63],"with":[64],"international":[66],"phonetic":[67],"alphabet":[68],"(IPA).":[69],"To":[70],"verify":[71],"FSA,":[72],"large":[74],"scale":[75],"corpus":[77],"was":[78],"used":[79],"train":[81],"Time-delay":[82],"neural":[83],"networks":[84],"(TDNN)":[85],"based":[86],"on":[87,93,105,112,153],"models,":[90],"and":[91,114],"tested":[92,148],"Russian":[94],"learner":[95],"data":[96],"set.":[97],"Experimental":[98],"results":[99],"showed":[100],"that":[101,129],"all":[102],"FSA's":[103],"accuracy":[104,117,161],"test":[107],"set":[108],"about":[110,159],"95%":[111],"average,":[113],"diagnosis":[116],"FSA-based":[120,151],"achieved":[123,158],"2.2%":[125],"improvement":[126],"compared":[127],"segment-based":[131],"baseline":[132],"system.":[133],"Besides,":[134],"as":[135],"FSA":[137],"theoretically":[139],"capable":[140],"language-universal":[143],"attributes,":[145],"also":[147],"trained":[150],"method":[152],"native":[154],"English":[155],"corpus,":[156],"50%":[160],"rate.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}