{"id":"https://openalex.org/W2750356407","doi":"https://doi.org/10.21437/interspeech.2017-1350","title":"Phonological Feature Based Mispronunciation Detection and Diagnosis Using Multi-Task DNNs and Active Learning","display_name":"Phonological Feature Based Mispronunciation Detection and Diagnosis Using Multi-Task DNNs and Active Learning","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2750356407","doi":"https://doi.org/10.21437/interspeech.2017-1350","mag":"2750356407"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1350","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1350","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/A5011121139","display_name":"Vipul Arora","orcid":"https://orcid.org/0000-0002-1207-1258"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Vipul Arora","raw_affiliation_strings":["Faculty of Linguistics, Philology and Phonetics, University of Oxford, UK"],"affiliations":[{"raw_affiliation_string":"Faculty of Linguistics, Philology and Phonetics, University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Aditi Lahiri","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Aditi Lahiri","raw_affiliation_strings":["Faculty of Linguistics, Philology and Phonetics, University of Oxford, UK"],"affiliations":[{"raw_affiliation_string":"Faculty of Linguistics, Philology and Phonetics, University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049324185","display_name":"Henning Reetz","orcid":null},"institutions":[{"id":"https://openalex.org/I114090438","display_name":"Goethe University Frankfurt","ror":"https://ror.org/04cvxnb49","country_code":"DE","type":"education","lineage":["https://openalex.org/I114090438"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Henning Reetz","raw_affiliation_strings":["Goethe University, Frankfurt am Main, Germany"],"affiliations":[{"raw_affiliation_string":"Goethe University, Frankfurt am Main, Germany","institution_ids":["https://openalex.org/I114090438"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011121139"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":1.8709,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89327532,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1432","last_page":"1436"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9980999827384949,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8255280256271362},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.752770185470581},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6271423101425171},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5940039753913879},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5793283581733704},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5791870355606079},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49391061067581177},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.482499361038208},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3295174837112427},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32851535081863403},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32291704416275024}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8255280256271362},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.752770185470581},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6271423101425171},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5940039753913879},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5793283581733704},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5791870355606079},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49391061067581177},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.482499361038208},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3295174837112427},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32851535081863403},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32291704416275024},{"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":2,"locations":[{"id":"doi:10.21437/interspeech.2017-1350","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1350","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:69032bc7-d9b0-45e6-b624-2822097a6f33","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:69032bc7-d9b0-45e6-b624-2822097a6f33","pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference item"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8799999952316284,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W81442308","https://openalex.org/W290344559","https://openalex.org/W330298975","https://openalex.org/W334543181","https://openalex.org/W1499332833","https://openalex.org/W1753200545","https://openalex.org/W1985084205","https://openalex.org/W2010800472","https://openalex.org/W2091856355","https://openalex.org/W2094035326","https://openalex.org/W2095629250","https://openalex.org/W2137630452","https://openalex.org/W2146502635","https://openalex.org/W2147347517","https://openalex.org/W2170234362","https://openalex.org/W2399644537","https://openalex.org/W2401896499","https://openalex.org/W2405178423","https://openalex.org/W2407240503","https://openalex.org/W2408387233","https://openalex.org/W2509051157","https://openalex.org/W2512506745","https://openalex.org/W2552635739","https://openalex.org/W2587104096","https://openalex.org/W2903158431"],"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/W2361861616","https://openalex.org/W2776838583","https://openalex.org/W4205510397"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,16,40,47],"phonological":[4,53],"feature":[5],"based":[6,63,114,129],"computer":[7],"aided":[8],"pronunciation":[9],"training":[10],"system":[11,107],"for":[12,50,87,94],"the":[13,24,30,52,71,83,104,124],"learners":[14],"of":[15,39,73,126],"new":[17],"language":[18],"(L2).":[19],"Phonological":[20],"features":[21,54],"allow":[22],"analysing":[23],"learners\u2019":[25],"mispronunciations":[26],"systematically":[27],"and":[28,55,96,112],"rendering":[29],"feedback":[31],"more":[32,118],"effectively.":[33],"The":[34],"proposed":[35,66,105],"acoustic":[36],"model":[37],"consists":[38],"multi-task":[41],"deep":[42],"neural":[43],"network,":[44],"which":[45,75],"uses":[46],"shared":[48],"representation":[49],"estimating":[51],"HMM":[56],"state":[57],"probabilities.":[58],"Moreover,":[59],"an":[60],"active":[61,127],"learning":[62,128],"scheme":[64],"is":[65,76],"to":[67],"efficiently":[68],"deal":[69],"with":[70],"cost":[72],"annotation,":[74],"done":[77],"by":[78,81],"expert":[79],"teachers,":[80],"selecting":[82],"most":[84],"informative":[85],"samples":[86],"annotation.":[88],"Experimental":[89],"evaluations":[90],"are":[91],"carried":[92],"out":[93],"German":[95],"Italian":[97],"native-speakers":[98],"speaking":[99],"English.":[100],"For":[101],"mispronunciation":[102],"detection,":[103],"feature-based":[106],"outperforms":[108],"conventional":[109],"GOP":[110],"measure":[111],"classifier":[113],"methods,":[115],"while":[116],"providing":[117],"detailed":[119],"diagnosis.":[120],"Evaluations":[121],"also":[122],"demonstrate":[123],"advantage":[125],"sampling":[130],"over":[131],"random":[132],"sampling.":[133]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}