{"id":"https://openalex.org/W3140560950","doi":"https://doi.org/10.1109/slt48900.2021.9383590","title":"Analysis of Multimodal Features for Speaking Proficiency Scoring in an Interview Dialogue","display_name":"Analysis of Multimodal Features for Speaking Proficiency Scoring in an Interview Dialogue","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3140560950","doi":"https://doi.org/10.1109/slt48900.2021.9383590","mag":"3140560950"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383590","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383590","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/A5065997585","display_name":"Mao Saeki","orcid":"https://orcid.org/0000-0002-1825-2236"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Mao Saeki","raw_affiliation_strings":["Waseda University, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078242198","display_name":"Yoichi Matsuyama","orcid":"https://orcid.org/0000-0003-0282-6482"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoichi Matsuyama","raw_affiliation_strings":["Waseda University, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024724493","display_name":"Satoshi Kobashikawa","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Kobashikawa","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087632404","display_name":"Tetsuji Ogawa","orcid":"https://orcid.org/0000-0002-7316-2073"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuji Ogawa","raw_affiliation_strings":["Waseda University, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101188700","display_name":"Tetsunori Kobayashi","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsunori Kobayashi","raw_affiliation_strings":["Waseda University, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5065997585"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":1.3597,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.841124,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"629","last_page":"635"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9973999857902527,"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/T12031","display_name":"Speech and dialogue systems","score":0.9973999857902527,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11148","display_name":"Language, Metaphor, and Cognition","score":0.9842000007629395,"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":0.7732675075531006},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6145982146263123},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5735575556755066},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5534784197807312},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5430487990379333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45986366271972656},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3811505138874054}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7732675075531006},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6145982146263123},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5735575556755066},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5534784197807312},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5430487990379333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45986366271972656},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3811505138874054},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383590","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383590","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":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322638","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W59873036","https://openalex.org/W1628791547","https://openalex.org/W1793121960","https://openalex.org/W2016114400","https://openalex.org/W2061504941","https://openalex.org/W2304127486","https://openalex.org/W2565056043","https://openalex.org/W2580032371","https://openalex.org/W2803039862","https://openalex.org/W2805082944","https://openalex.org/W2807126412","https://openalex.org/W2807245740","https://openalex.org/W2896457183","https://openalex.org/W2939437245","https://openalex.org/W2948090285","https://openalex.org/W2951008357","https://openalex.org/W2963341956","https://openalex.org/W2967893836","https://openalex.org/W2971194149","https://openalex.org/W2973798050","https://openalex.org/W2979668382","https://openalex.org/W2997578171","https://openalex.org/W3037895476","https://openalex.org/W6602444719","https://openalex.org/W6638318767","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"This":[0],"paper":[1],"analyzes":[2],"the":[3,31,59,111,118,141],"effectiveness":[4,112],"of":[5,18,23,33,61,90,96,113,143],"different":[6],"modalities":[7],"in":[8,13,140],"automated":[9,74],"speaking":[10,75,98],"proficiency":[11,76],"scoring":[12,77,131],"an":[14,73,85],"online":[15,86],"dialogue":[16],"task":[17],"non-native":[19],"speakers.":[20],"Conversational":[21],"competence":[22],"a":[24,126],"language":[25],"learner":[26],"can":[27],"be":[28],"assessed":[29],"through":[30],"use":[32],"multimodal":[34],"behaviors":[35],"such":[36,64],"as":[37,65],"speech":[38],"content,":[39],"prosody,":[40],"and":[41,46,68,109,146],"visual":[42,62,107,147],"cues.":[43],"Although":[44],"lexical":[45],"acoustic":[47],"features":[48,108],"have":[49],"been":[50,55],"widely":[51],"studied,":[52],"there":[53],"has":[54],"no":[56],"study":[57],"on":[58],"usage":[60],"features,":[63,81],"facial":[66],"expressions":[67],"eye":[69],"gaze.":[70],"To":[71],"build":[72],"system":[78],"using":[79],"multi-modal":[80],"we":[82],"first":[83],"constructed":[84],"video":[87],"interview":[88],"dataset":[89],"210":[91],"Japanese":[92],"English-learners":[93],"with":[94,121,129,134],"annotations":[95],"their":[97],"proficiency.":[99],"We":[100],"then":[101],"examined":[102],"two":[103],"approaches":[104],"for":[105],"incorporating":[106],"compared":[110],"each":[114],"modality.":[115],"Results":[116],"show":[117],"end-to-end":[119],"approach":[120],"deep":[122],"neural":[123],"networks":[124],"achieves":[125],"higher":[127],"correlation":[128],"human":[130],"than":[132],"one":[133],"handcrafted":[135],"features.":[136,148],"Modalities":[137],"are":[138],"effective":[139],"order":[142],"lexical,":[144],"acoustic,":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}