{"id":"https://openalex.org/W1993166555","doi":"https://doi.org/10.1109/iscslp.2012.6423538","title":"Improve mispronunciation detection with Tandem feature","display_name":"Improve mispronunciation detection with Tandem feature","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W1993166555","doi":"https://doi.org/10.1109/iscslp.2012.6423538","mag":"1993166555"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2012.6423538","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423538","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 8th International Symposium on Chinese Spoken Language Processing","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/A5100642860","display_name":"Hua Yuan","orcid":"https://orcid.org/0000-0001-7594-8718"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Yuan","raw_affiliation_strings":["Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, China","[Tsinghua National Laboratory for Information Science and Technology Department of Electronic Engineering, Tsinghua University, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"[Tsinghua National Laboratory for Information Science and Technology Department of Electronic Engineering, Tsinghua University, China]","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048022062","display_name":"Junhong Zhao","orcid":"https://orcid.org/0000-0001-7031-3828"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210107198","display_name":"State Key Laboratory of Transducer Technology","ror":"https://ror.org/01qg56n75","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366","https://openalex.org/I19820366","https://openalex.org/I4210107198","https://openalex.org/I4210110458","https://openalex.org/I4210147322"]},{"id":"https://openalex.org/I4210110458","display_name":"Institute of Electronics","ror":"https://ror.org/01z143507","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210110458"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhong Zhao","raw_affiliation_strings":["University of Chinese Academy of Sciences, China","State Key Laboratory on Transducing Technology, Institute of Electronics, Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory on Transducing Technology, Institute of Electronics, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210107198","https://openalex.org/I4210110458"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100409741","display_name":"Jia Liu","orcid":"https://orcid.org/0000-0003-0383-0934"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Liu","raw_affiliation_strings":["Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, China","[Tsinghua National Laboratory for Information Science and Technology Department of Electronic Engineering, Tsinghua University, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"[Tsinghua National Laboratory for Information Science and Technology Department of Electronic Engineering, Tsinghua University, China]","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5203,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.59675961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"184","last_page":"187"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9990000128746033,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9966999888420105,"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/computer-science","display_name":"Computer science","score":0.8000277876853943},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7446281909942627},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7399027943611145},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7361963391304016},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6794390082359314},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6007111668586731},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.5825067758560181},{"id":"https://openalex.org/keywords/tandem","display_name":"Tandem","score":0.500969648361206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44909390807151794},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42316633462905884},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3448951542377472},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10559073090553284},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06803280115127563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8000277876853943},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7446281909942627},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7399027943611145},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7361963391304016},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6794390082359314},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6007111668586731},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.5825067758560181},{"id":"https://openalex.org/C2777814067","wikidata":"https://www.wikidata.org/wiki/Q1752317","display_name":"Tandem","level":2,"score":0.500969648361206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44909390807151794},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42316633462905884},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3448951542377472},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10559073090553284},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06803280115127563},{"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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace 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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2012.6423538","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423538","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 8th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W290344559","https://openalex.org/W296713244","https://openalex.org/W1994126409","https://openalex.org/W2008834750","https://openalex.org/W2016114400","https://openalex.org/W2025009046","https://openalex.org/W2046932483","https://openalex.org/W2071401855","https://openalex.org/W2091650508","https://openalex.org/W2134124280","https://openalex.org/W2165712214","https://openalex.org/W2399153411","https://openalex.org/W2404722202","https://openalex.org/W2406677277","https://openalex.org/W4229742165","https://openalex.org/W6712585555","https://openalex.org/W6713887538"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W2366752344"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3],"method":[4],"to":[5,24,43,69,85],"improve":[6,86],"the":[7,26,45,63,73,87,90,100,109],"mispronunciation":[8],"detection":[9],"performance":[10],"for":[11],"low-resource":[12,27],"acoustic":[13],"model.":[14],"The":[15,31,77],"1h":[16],"speech":[17,65],"data":[18,66],"is":[19,41,67,80,95,104],"randomly":[20],"selected":[21],"from":[22,35],"CU-CHLOE":[23],"imitate":[25],"non-native":[28],"English":[29,60],"situation.":[30],"Tandem":[32,78],"feature":[33,48,79],"derived":[34],"articulatory":[36,75],"based":[37],"Multi-Layer":[38],"Perception":[39],"(MLP)":[40],"employed":[42],"replace":[44],"traditional":[46],"spectral":[47],"(e.g.":[49],"PLP).":[50],"Further,":[51],"motivated":[52],"by":[53,97,106],"similar":[54],"pronunciation":[55],"characteristics":[56],"between":[57],"Chinese":[58],"speaking":[59],"and":[61,99],"Mandarin,":[62],"Mandarin":[64],"used":[68],"assist":[70],"in":[71],"training":[72],"multilingual":[74],"MLPs.":[76],"also":[81],"combined":[82],"with":[83,108],"PLP":[84],"performance.":[88],"Finally,":[89],"phone":[91],"recognition":[92],"correctness":[93],"(CORR)":[94],"improved":[96,105],"3.84%,":[98],"diagnosis":[101],"accuracy":[102],"(DA)":[103],"2.25%":[107],"proposed":[110],"method.":[111]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
