{"id":"https://openalex.org/W2067517679","doi":"https://doi.org/10.1109/slt.2012.6424254","title":"A comparison-based approach to mispronunciation detection","display_name":"A comparison-based approach to mispronunciation detection","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2067517679","doi":"https://doi.org/10.1109/slt.2012.6424254","mag":"2067517679"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2012.6424254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2012.6424254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1721.1/75660","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084509956","display_name":"Ann Lee","orcid":"https://orcid.org/0000-0003-4300-9032"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ann Lee","raw_affiliation_strings":["MIT Computer Science, Artificial Intelligence Laboratory, Cambridge, MA, USA","MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, Massachusetts 02139, USA"],"affiliations":[{"raw_affiliation_string":"MIT Computer Science, Artificial Intelligence Laboratory, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, Massachusetts 02139, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["MIT Computer Science, Artificial Intelligence Laboratory, Cambridge, MA, USA","MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, Massachusetts 02139, USA"],"affiliations":[{"raw_affiliation_string":"MIT Computer Science, Artificial Intelligence Laboratory, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, Massachusetts 02139, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5084509956"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.4213,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.94389834,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"382","last_page":"387"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976000189781189,"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":0.9976000189781189,"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/T11309","display_name":"Music and Audio Processing","score":0.9968000054359436,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.991100013256073,"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/computer-science","display_name":"Computer science","score":0.8419821262359619},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.8073081970214844},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.8048450350761414},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7033348083496094},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6828980445861816},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6393576860427856},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.580436110496521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5040354132652283},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.47006186842918396},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4526670575141907},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44051626324653625},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1194276213645935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8419821262359619},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8073081970214844},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.8048450350761414},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7033348083496094},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6828980445861816},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6393576860427856},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.580436110496521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5040354132652283},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.47006186842918396},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4526670575141907},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44051626324653625},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1194276213645935},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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":3,"locations":[{"id":"doi:10.1109/slt.2012.6424254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2012.6424254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.299.9374","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.299.9374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://groups.csail.mit.edu/sls//publications/2012/Lee-Ann_SLT12.pdf","raw_type":"text"},{"id":"pmh:oai:dspace.mit.edu:1721.1/75660","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/75660","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/75660","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/75660","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W103312509","https://openalex.org/W273093436","https://openalex.org/W275138538","https://openalex.org/W1541169815","https://openalex.org/W2095514769","https://openalex.org/W2114492809","https://openalex.org/W2118474530","https://openalex.org/W2126203737","https://openalex.org/W2134124280","https://openalex.org/W2137268753","https://openalex.org/W2139008940","https://openalex.org/W2147229100","https://openalex.org/W2152334841","https://openalex.org/W2153635508","https://openalex.org/W2154093685","https://openalex.org/W2161969291","https://openalex.org/W2171019095","https://openalex.org/W6610146026"],"related_works":["https://openalex.org/W2341338763","https://openalex.org/W2950183183","https://openalex.org/W2030799363","https://openalex.org/W2032415964","https://openalex.org/W2288425735","https://openalex.org/W2349923317","https://openalex.org/W2894081631","https://openalex.org/W2986063033","https://openalex.org/W2529301793","https://openalex.org/W2947571721"],"abstract_inverted_index":{"The":[0],"task":[1,132],"of":[2,20,32,40,96,112],"mispronunciation":[3],"detection":[4,131],"for":[5,57],"language":[6],"learning":[7],"is":[8,68],"typically":[9],"accomplished":[10],"via":[11],"automatic":[12],"speech":[13],"recognition":[14],"(ASR).":[15],"Unfortunately,":[16],"less":[17],"than":[18],"2%":[19],"the":[21,29,94,99,103,120,124],"world's":[22],"languages":[23],"have":[24],"an":[25,34,138],"ASR":[26,35],"capability,":[27],"and":[28,77,83,89,102],"conventional":[30],"process":[31],"creating":[33],"system":[36],"requires":[37],"large":[38],"quantities":[39],"expensive,":[41],"annotated":[42],"data.":[43],"In":[44],"this":[45],"paper":[46],"we":[47,84],"report":[48],"on":[49,86,108,127],"our":[50],"efforts":[51],"to":[52,137],"develop":[53],"a":[54,72,78,109,128],"comparison-based":[55],"framework":[56,122],"detecting":[58],"word-level":[59,88],"mispronunciations":[60],"in":[61,98],"nonnative":[62,116],"speech.":[63],"Dynamic":[64],"time":[65],"warping":[66,100],"(DTW)":[67],"carried":[69],"out":[70],"between":[71],"student's":[73],"(non-native":[74],"speaker)":[75,81],"utterance":[76],"teacher's":[79],"(native":[80],"utterance,":[82],"focus":[85],"extracting":[87],"phone-level":[90],"features":[91],"that":[92,119,140],"describe":[93],"degree":[95],"mis-alignment":[97],"path":[101],"distance":[104],"matrix.":[105],"Experimental":[106],"results":[107],"Chinese":[110],"University":[111],"Hong":[113],"Kong":[114],"(CUHK)":[115],"corpus":[117],"show":[118],"proposed":[121],"improves":[123],"relative":[125],"performance":[126],"mispronounced":[129],"word":[130],"by":[133],"nearly":[134],"50%":[135],"compared":[136],"approach":[139],"only":[141],"considers":[142],"DTW":[143],"alignment":[144],"scores.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
