{"id":"https://openalex.org/W3148504935","doi":"https://doi.org/10.1109/slt48900.2021.9383553","title":"Automated Scoring of Spontaneous Speech from Young Learners of English Using Transformers","display_name":"Automated Scoring of Spontaneous Speech from Young Learners of English Using Transformers","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3148504935","doi":"https://doi.org/10.1109/slt48900.2021.9383553","mag":"3148504935"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383553","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383553","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/A5100772594","display_name":"Xinhao Wang","orcid":"https://orcid.org/0000-0002-0366-7543"},"institutions":[{"id":"https://openalex.org/I1341030882","display_name":"Educational Testing Service","ror":"https://ror.org/03b5q4637","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1341030882"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xinhao Wang","raw_affiliation_strings":["Educational Testing Service, San Francisco, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Educational Testing Service, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1341030882"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030816616","display_name":"Keelan Evanini","orcid":"https://orcid.org/0000-0003-4243-3376"},"institutions":[{"id":"https://openalex.org/I1341030882","display_name":"Educational Testing Service","ror":"https://ror.org/03b5q4637","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1341030882"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keelan Evanini","raw_affiliation_strings":["Educational Testing Service, Princeton, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Educational Testing Service, Princeton, NJ, USA","institution_ids":["https://openalex.org/I1341030882"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342006","display_name":"Yao Qian","orcid":"https://orcid.org/0000-0003-1855-9630"},"institutions":[{"id":"https://openalex.org/I1341030882","display_name":"Educational Testing Service","ror":"https://ror.org/03b5q4637","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1341030882"]},{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yao Qian","raw_affiliation_strings":["Microsoft, Educational Testing Service, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Educational Testing Service, Redmond, WA, USA","institution_ids":["https://openalex.org/I1341030882","https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108692434","display_name":"Matthew Mulholland","orcid":null},"institutions":[{"id":"https://openalex.org/I1341030882","display_name":"Educational Testing Service","ror":"https://ror.org/03b5q4637","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1341030882"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Mulholland","raw_affiliation_strings":["Educational Testing Service, Princeton, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Educational Testing Service, Princeton, NJ, USA","institution_ids":["https://openalex.org/I1341030882"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100772594"],"corresponding_institution_ids":["https://openalex.org/I1341030882"],"apc_list":null,"apc_paid":null,"fwci":1.3992,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.8462372,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"705","last_page":"712"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9986000061035156,"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/T10028","display_name":"Topic Modeling","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7756633758544922},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6649740934371948},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.573847234249115},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5426519513130188},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5404731631278992},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.516883134841919},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5056765079498291},{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.49892711639404297},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4761400520801544},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.4649656414985657},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4371644854545593},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35824453830718994},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2843356728553772}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7756633758544922},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6649740934371948},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.573847234249115},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5426519513130188},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5404731631278992},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.516883134841919},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5056765079498291},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.49892711639404297},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4761400520801544},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.4649656414985657},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4371644854545593},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35824453830718994},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2843356728553772},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383553","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383553","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8299999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1032614754","https://openalex.org/W1524333225","https://openalex.org/W2101234009","https://openalex.org/W2116983617","https://openalex.org/W2129006464","https://openalex.org/W2157574624","https://openalex.org/W2250817048","https://openalex.org/W2250874787","https://openalex.org/W2404292492","https://openalex.org/W2510063686","https://openalex.org/W2749298174","https://openalex.org/W2799054028","https://openalex.org/W2896457183","https://openalex.org/W2899663614","https://openalex.org/W2912981563","https://openalex.org/W2921829459","https://openalex.org/W2923014074","https://openalex.org/W2962739339","https://openalex.org/W2963078909","https://openalex.org/W2963310665","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2964110616","https://openalex.org/W2970597249","https://openalex.org/W3094704668","https://openalex.org/W4385245566","https://openalex.org/W6631362777","https://openalex.org/W6675354045","https://openalex.org/W6691654054","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6755977528","https://openalex.org/W6763701032","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W2365169615","https://openalex.org/W1970538215","https://openalex.org/W2400151637","https://openalex.org/W2975827637","https://openalex.org/W2354089692","https://openalex.org/W595497825","https://openalex.org/W4236323843","https://openalex.org/W2002616876","https://openalex.org/W3174418441","https://openalex.org/W2383111961"],"abstract_inverted_index":{"This":[0],"study":[1,36],"explores":[2],"the":[3,9,31,34,67,97,101,146,149,152,177,185],"use":[4],"of":[5,12,33,57,73,96,148,173],"Transformer-based":[6,83,150],"models":[7,42,84,98],"for":[8,19,119],"automated":[10,40,153],"assessment":[11],"children's":[13,79],"non-native":[14,80],"spontaneous":[15,81],"speech.":[16,82],"Traditional":[17],"approaches":[18],"this":[20],"task":[21],"have":[22],"relied":[23],"heavily":[24],"on":[25,45,78],"delivery":[26],"features":[27],"(e.g.,":[28,60],"fluency),":[29],"whereas":[30],"goal":[32],"current":[35],"is":[37],"to":[38,49,108],"build":[39],"scoring":[41],"based":[43],"solely":[44],"transcriptions":[46,90],"in":[47,106],"order":[48,107],"see":[50],"how":[51],"well":[52],"they":[53],"capture":[54],"additional":[55],"aspects":[56],"speaking":[58],"proficiency":[59,167],"content":[61,112],"appropriateness,":[62],"vocabulary,":[63],"and":[64,91,94,132,184],"grammar)":[65],"despite":[66],"high":[68],"word":[69],"error":[70],"rate":[71],"(WER)":[72],"automatic":[74],"speech":[75],"recognition":[76],"(ASR)":[77],"are":[85],"built":[86],"using":[87,156],"both":[88,176],"manual":[89],"ASR":[92,157],"hypotheses,":[93],"versions":[95],"that":[99],"incorporated":[100],"prompt":[102],"text":[103],"were":[104,117],"investigated":[105],"more":[109],"directly":[110],"measure":[111],"appropriateness.":[113],"Two":[114],"baseline":[115,180,187],"systems":[116],"used":[118],"comparison,":[120],"including":[121],"an":[122],"attention-based":[123,178],"Long":[124],"Short-Term":[125],"Memory":[126],"(LSTM)":[127],"Recurrent":[128],"Neural":[129],"Network":[130],"(RNN)":[131],"a":[133,160],"Support":[134],"Vector":[135],"Regressor":[136],"(SVR)":[137],"with":[138,165],"manually":[139],"engineered":[140],"content-related":[141],"features.":[142],"Experimental":[143],"results":[144],"demonstrate":[145],"effectiveness":[147],"models:":[151],"prompt-aware":[154],"model":[155],"hypotheses":[158],"achieves":[159],"Pearson":[161],"correlation":[162],"coefficient":[163],"(r)":[164],"holistic":[166],"scores":[168],"provided":[169],"by":[170],"human":[171],"experts":[172],"0.835,":[174],"outperforming":[175],"RNN-LSTM":[179],"(r":[181,188],"=":[182,189],"0.791)":[183],"SVR":[186],"0.767).":[190]},"counts_by_year":[{"year":2026,"cited_by_count":26},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-05-28T09:10:13.091523","created_date":"2025-10-10T00:00:00"}