{"id":"https://openalex.org/W2787455262","doi":"https://doi.org/10.1109/apsipa.2017.8282103","title":"A study on landmark detection based on CTC and its application to pronunciation error detection","display_name":"A study on landmark detection based on CTC and its application to pronunciation error detection","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2787455262","doi":"https://doi.org/10.1109/apsipa.2017.8282103","mag":"2787455262"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2017.8282103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5061918821","display_name":"Chuanying Niu","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":true,"raw_author_name":"Chuanying Niu","raw_affiliation_strings":["Beijing Language and Culture University, Beijing, china"],"affiliations":[{"raw_affiliation_string":"Beijing Language and Culture University, Beijing, china","institution_ids":["https://openalex.org/I115212828"]}]},{"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 Language and Culture University, Beijing, china"],"affiliations":[{"raw_affiliation_string":"Beijing Language and Culture University, Beijing, china","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059726557","display_name":"Xuesong Yang","orcid":"https://orcid.org/0000-0001-8625-5044"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuesong Yang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"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 Language and Culture University, Beijing, china"],"affiliations":[{"raw_affiliation_string":"Beijing Language and Culture University, Beijing, china","institution_ids":["https://openalex.org/I115212828"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061918821"],"corresponding_institution_ids":["https://openalex.org/I115212828"],"apc_list":null,"apc_paid":null,"fwci":0.9751,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.82962819,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"636","last_page":"640"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9933000206947327,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.8614912629127502},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8491746187210083},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7641341090202332},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6346410512924194},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.632199227809906},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5816180109977722},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5780083537101746},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5755774974822998},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5446741580963135},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47623756527900696},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3520432114601135}],"concepts":[{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.8614912629127502},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8491746187210083},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7641341090202332},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6346410512924194},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.632199227809906},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5816180109977722},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5780083537101746},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5755774974822998},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5446741580963135},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47623756527900696},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3520432114601135},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/apsipa.2017.8282103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320325046","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W7155391","https://openalex.org/W12857174","https://openalex.org/W98262776","https://openalex.org/W287073639","https://openalex.org/W1494198834","https://openalex.org/W1967177300","https://openalex.org/W1970533835","https://openalex.org/W2045956438","https://openalex.org/W2119155265","https://openalex.org/W2127141656","https://openalex.org/W2132049498","https://openalex.org/W2134124280","https://openalex.org/W2139008940","https://openalex.org/W2398529454","https://openalex.org/W2403033074","https://openalex.org/W2403199234","https://openalex.org/W2407648438","https://openalex.org/W2489383278","https://openalex.org/W2508915748","https://openalex.org/W2510945575","https://openalex.org/W2575689684","https://openalex.org/W2881925123","https://openalex.org/W2963211739","https://openalex.org/W4242640703","https://openalex.org/W4245838404","https://openalex.org/W6600298696","https://openalex.org/W6629717138","https://openalex.org/W6712710612","https://openalex.org/W6713505222","https://openalex.org/W6713982112"],"related_works":["https://openalex.org/W3104406212","https://openalex.org/W2139795704","https://openalex.org/W2962866381","https://openalex.org/W2086667971","https://openalex.org/W2773832794","https://openalex.org/W2136389896","https://openalex.org/W2075329984","https://openalex.org/W3188060693","https://openalex.org/W3164643878","https://openalex.org/W3094947935","https://openalex.org/W3134482008","https://openalex.org/W3012447314","https://openalex.org/W3014677573","https://openalex.org/W2075224964","https://openalex.org/W3132072393","https://openalex.org/W3207490364","https://openalex.org/W2997208288","https://openalex.org/W2395845374","https://openalex.org/W3015439711","https://openalex.org/W1491807228"],"abstract_inverted_index":{"Acoustic":[0],"features":[1],"extracted":[2],"in":[3,15,123,156],"the":[4,108,120,124],"vicinity":[5],"of":[6,23,35,50,110,114,139,162],"landmarks":[7,26,58,121],"have":[8],"demonstrated":[9],"their":[10],"usefulness":[11],"for":[12,71],"detecting":[13,24],"mispronunciation":[14],"our":[16],"recent":[17],"work":[18],"[1,":[19],"2].":[20],"Traditional":[21],"approaches":[22],"acoustic":[25,78],"rely":[27],"on":[28,85],"annotations":[29],"by":[30,102],"linguists":[31],"with":[32,68,91,119],"prior":[33],"knowledge":[34],"speech":[36],"production":[37],"mechanisms,":[38],"which":[39,99],"are":[40,117,133],"laborious":[41],"and":[42,129],"expensive.":[43],"This":[44],"paper":[45],"proposes":[46],"a":[47,86],"data-driven":[48,128,147],"approach":[49],"connectionist":[51],"temporal":[52],"classification":[53],"(CTC)":[54],"that":[55,107,146],"can":[56,164],"detect":[57,136],"without":[59],"any":[60],"human":[61],"labels":[62,83],"while":[63],"still":[64],"maintaining":[65],"consistent":[66,118],"performance":[67],"knowledge-based":[69,130,154],"models":[70,132],"stop":[72],"burst":[73],"landmarks.":[74],"We":[75,105],"designed":[76],"an":[77],"model":[79,116,150,155],"to":[80,135,153],"predict":[81],"phone":[82,112],"based":[84],"recurrent":[87],"neural":[88],"network":[89],"(RNN)":[90],"bidirectional":[92],"long":[93],"short-":[94],"term":[95],"memory":[96],"(BLSTM)":[97],"units,":[98],"is":[100,151],"trained":[101],"CTC":[103,148],"technique.":[104],"found":[106],"positions":[109],"spiky":[111],"outputs":[113],"this":[115],"annotated":[122],"TIMIT":[125],"corpus.":[126],"Both":[127],"landmark":[131,149],"applied":[134],"pronunciation":[137,157],"errors":[138],"second-language":[140],"(L2)":[141],"Chinese":[142],"learners.":[143],"Experiments":[144],"illustrate":[145],"comparable":[152],"error":[158],"detection.":[159],"The":[160],"fusion":[161],"them":[163],"further":[165],"improve":[166],"performance.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}