{"id":"https://openalex.org/W2137469438","doi":"https://doi.org/10.1109/icassp.2008.4518800","title":"Automatic mispronunciation detection for Mandarin","display_name":"Automatic mispronunciation detection for Mandarin","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2137469438","doi":"https://doi.org/10.1109/icassp.2008.4518800","mag":"2137469438"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518800","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal 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/A5067426591","display_name":"Feng Zhang","orcid":"https://orcid.org/0000-0001-8765-9032"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Zhang","raw_affiliation_strings":["IFlytek Speech Laboratory, University of Science and Technology, Hefei, China","Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFlytek Speech Laboratory, University of Science and Technology, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009913582","display_name":"Chao Huang","orcid":"https://orcid.org/0000-0002-9300-1787"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Huang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Frank K. Soong","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104229610","display_name":"Min Chu","orcid":null},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Chu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102734836","display_name":"Ren-Hua Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renhua Wang","raw_affiliation_strings":["IFlytek Speech Laboratory, University of Science and Technology, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFlytek Speech Laboratory, University of Science and Technology, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.323,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":{"value":0.87516542,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5077","last_page":"5080"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10860","display_name":"Speech and Audio Processing","score":0.9955000281333923,"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":0.9847999811172485,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8759982585906982},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.8340058922767639},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7584660053253174},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7282689809799194},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6947938799858093},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.6001085042953491},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5233539938926697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3959488868713379},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0808209776878357}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8759982585906982},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8340058922767639},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7584660053253174},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7282689809799194},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6947938799858093},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.6001085042953491},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5233539938926697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3959488868713379},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0808209776878357},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/icassp.2008.4518800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518800","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7799999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W103312509","https://openalex.org/W105558132","https://openalex.org/W334543181","https://openalex.org/W1512429158","https://openalex.org/W1599512239","https://openalex.org/W1999494183","https://openalex.org/W2002342963","https://openalex.org/W2041086022","https://openalex.org/W2402676007","https://openalex.org/W6604305248","https://openalex.org/W6630838124"],"related_works":["https://openalex.org/W2359820297","https://openalex.org/W2032265864","https://openalex.org/W1964091558","https://openalex.org/W2094188777","https://openalex.org/W2580589825","https://openalex.org/W2110864561","https://openalex.org/W2069086264","https://openalex.org/W2108904499","https://openalex.org/W2137469438","https://openalex.org/W2350941553"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,7,31,79],"methods":[4],"to":[5,29,55,90,97],"improve":[6],"performance":[8],"of":[9,34,40,48,67,82],"mispronunciation":[10],"detection":[11],"at":[12,92],"syllable":[13],"level":[14],"for":[15],"Mandarin":[16],"from":[17,88],"two":[18],"aspects:":[19],"proposing":[20],"scaled":[21],"log-posterior":[22],"probability":[23],"(SLPP)":[24],"and":[25,45,95],"weighted":[26],"phone":[27],"SLPP":[28],"get":[30,56],"better":[32,58],"measure":[33],"pronunciation":[35,76],"quality;":[36],"introducing":[37],"speaker":[38,41,46],"normalization":[39],"adaptive":[42],"training":[43],"(SAT)":[44],"adaptation":[47],"selective":[49],"maximum":[50],"likelihood":[51],"linear":[52],"regression":[53],"(SMLLR)":[54],"a":[57,64],"statistical":[59],"model.":[60],"Experiments":[61],"based":[62],"on":[63],"database,":[65],"consisting":[66],"8000":[68],"syllables":[69],"pronounced":[70],"by":[71,85],"40":[72],"speakers":[73],"with":[74],"varied":[75],"proficiency,":[77],"confirm":[78],"promising":[80],"effectiveness":[81],"these":[83],"strategies":[84],"reducing":[86],"FAR":[87],"41.1%":[89],"31.4%":[91],"90%":[93],"FRR":[94],"36.0%":[96],"16.3%at":[98],"95%FRR.":[99]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
