{"id":"https://openalex.org/W3015231007","doi":"https://doi.org/10.1109/icassp40776.2020.9052975","title":"SED-MDD: Towards Sentence Dependent End-To-End Mispronunciation Detection and Diagnosis","display_name":"SED-MDD: Towards Sentence Dependent End-To-End Mispronunciation Detection and Diagnosis","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015231007","doi":"https://doi.org/10.1109/icassp40776.2020.9052975","mag":"3015231007"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9052975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9052975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5104247873","display_name":"Yiqing Feng","orcid":"https://orcid.org/0009-0006-1238-0874"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqing Feng","raw_affiliation_strings":["Shenzhen Chinese Calligraphy Digital Simulation Engineering Laboratory, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Chinese Calligraphy Digital Simulation Engineering Laboratory, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006438734","display_name":"Guanyu Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanyu Fu","raw_affiliation_strings":["Shenzhen Chinese Calligraphy Digital Simulation Engineering Laboratory, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Chinese Calligraphy Digital Simulation Engineering Laboratory, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101895423","display_name":"Qingcai Chen","orcid":"https://orcid.org/0000-0001-8473-7293"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingcai Chen","raw_affiliation_strings":["Shenzhen Chinese Calligraphy Digital Simulation Engineering Laboratory, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Chinese Calligraphy Digital Simulation Engineering Laboratory, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100437924","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0001-6384-0355"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["Shenzhen Chinese Calligraphy Digital Simulation Engineering Laboratory, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Chinese Calligraphy Digital Simulation Engineering Laboratory, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3492","last_page":"3496"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.998199999332428,"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":0.9940999746322632,"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":0.7160340547561646},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6210705637931824},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5878139138221741},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.5756133794784546},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.528694748878479},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.47837916016578674},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42662158608436584},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42141973972320557},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3759973347187042},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1617991328239441}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7160340547561646},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6210705637931824},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5878139138221741},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.5756133794784546},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.528694748878479},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.47837916016578674},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42662158608436584},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42141973972320557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3759973347187042},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1617991328239441}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9052975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9052975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W296713244","https://openalex.org/W1635512741","https://openalex.org/W1836465849","https://openalex.org/W1869752048","https://openalex.org/W1924770834","https://openalex.org/W2074231493","https://openalex.org/W2077804127","https://openalex.org/W2137268753","https://openalex.org/W2163605009","https://openalex.org/W2400818677","https://openalex.org/W2552635739","https://openalex.org/W2803039862","https://openalex.org/W2888954148","https://openalex.org/W2889358387","https://openalex.org/W2889562042","https://openalex.org/W2890962360","https://openalex.org/W2895930397","https://openalex.org/W2938359332","https://openalex.org/W2963069010","https://openalex.org/W2963609956","https://openalex.org/W6610497376","https://openalex.org/W6638667902","https://openalex.org/W6639082767","https://openalex.org/W6684191040","https://openalex.org/W6713037690","https://openalex.org/W6736996214","https://openalex.org/W6754162995"],"related_works":["https://openalex.org/W2136652457","https://openalex.org/W2169849734","https://openalex.org/W2116722627","https://openalex.org/W2160171981","https://openalex.org/W2385954530","https://openalex.org/W1975869217","https://openalex.org/W2236912844","https://openalex.org/W2129150969","https://openalex.org/W2401728283","https://openalex.org/W2383829109"],"abstract_inverted_index":{"A":[0],"mispronunciation":[1,39,122],"detection":[2,40,123],"and":[3,20,41,50,54,74,82,102,109,124],"diagnosis":[4,42,125],"(MD&D)":[5,43,126],"system":[6],"typically":[7],"consists":[8],"of":[9,91,99,107,112],"multiple":[10],"stages,":[11,29],"such":[12],"as":[13,52],"an":[14,33,105],"acoustic":[15,73],"model,":[16],"a":[17,21,110],"language":[18],"model":[19,35,47,98,127],"Viterbi":[22],"decoder.":[23],"In":[24],"order":[25],"to":[26],"integrate":[27],"these":[28],"we":[30],"propose":[31],"SED-MDD,":[32],"end-to-end":[34,121],"for":[36],"sentence":[37],"dependent":[38],".":[44],"Our":[45,60],"proposed":[46],"takes":[48],"mel-spectrogram":[49],"characters":[51],"inputs":[53],"outputs":[55],"the":[56,68,79,85,89,96,119],"corresponding":[57],"phone":[58],"sequence.":[59],"experiments":[61],"prove":[62],"that":[63],"SED-MDD":[64,94],"can":[65],"implicitly":[66],"learn":[67],"phonological":[69,80],"rules":[70],"in":[71,84],"both":[72],"linguistic":[75],"features":[76],"directly":[77],"from":[78],"annotation":[81],"transcription":[83],"training":[86],"data.":[87],"To":[88],"best":[90],"our":[92],"knowledge,":[93],"is":[95],"first":[97],"its":[100],"kind":[101],"it":[103],"achieves":[104],"accuracy":[106],"86.35%":[108],"correctness":[111],"88.61%":[113],"on":[114],"L2-ARCTIC":[115],"which":[116],"significantly":[117],"outperforms":[118],"existing":[120],"CNN-RNN-CTC.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}