{"id":"https://openalex.org/W3016042119","doi":"https://doi.org/10.1109/icassp40776.2020.9054664","title":"Training Spoken Language Understanding Systems with Non-Parallel Speech and Text","display_name":"Training Spoken Language Understanding Systems with Non-Parallel Speech and Text","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016042119","doi":"https://doi.org/10.1109/icassp40776.2020.9054664","mag":"3016042119"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5003052411","display_name":"Leda Sar\u0131","orcid":"https://orcid.org/0000-0002-3754-1156"},"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":true,"raw_author_name":"Leda Sari","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, IL, US"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, IL, US","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":["IBM Research AI, NY, US"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, NY, US","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"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":"Mark Hasegawa-Johnson","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, IL, US"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, IL, US","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5003052411"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":1.7233,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.87451271,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"2018","issue":null,"first_page":"8109","last_page":"8113"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":1.0,"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":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9991000294685364,"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":0.8472880125045776},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.6883128881454468},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5787622928619385},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5659309029579163},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4478526711463928},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.41406798362731934},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.16578862071037292}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8472880125045776},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6883128881454468},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5787622928619385},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5659309029579163},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4478526711463928},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.41406798362731934},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.16578862071037292}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1523385540","https://openalex.org/W1550863320","https://openalex.org/W1614298861","https://openalex.org/W2017501150","https://openalex.org/W2085789144","https://openalex.org/W2112078429","https://openalex.org/W2128970689","https://openalex.org/W2166293310","https://openalex.org/W2184188583","https://openalex.org/W2347145335","https://openalex.org/W2473329891","https://openalex.org/W2786839803","https://openalex.org/W2888885488","https://openalex.org/W2891229414","https://openalex.org/W2894164357","https://openalex.org/W2896457183","https://openalex.org/W2917128112","https://openalex.org/W2931751229","https://openalex.org/W2950577311","https://openalex.org/W2963288440","https://openalex.org/W2963341956","https://openalex.org/W2964089584","https://openalex.org/W2972327934","https://openalex.org/W2972584841","https://openalex.org/W2973229104","https://openalex.org/W3007163346","https://openalex.org/W4206864474","https://openalex.org/W4231043689","https://openalex.org/W6631216910","https://openalex.org/W6636510571","https://openalex.org/W6684017090","https://openalex.org/W6686207219","https://openalex.org/W6755207826","https://openalex.org/W6759393636","https://openalex.org/W6761303817","https://openalex.org/W6807204625"],"related_works":["https://openalex.org/W4301342010","https://openalex.org/W158465921","https://openalex.org/W2261315194","https://openalex.org/W2099033952","https://openalex.org/W2520872336","https://openalex.org/W2339399820","https://openalex.org/W2338806053","https://openalex.org/W3204019825","https://openalex.org/W2003020325","https://openalex.org/W2164499211"],"abstract_inverted_index":{"End-to-end":[0],"spoken":[1],"language":[2],"understanding":[3],"(SLU)":[4],"systems":[5],"are":[6,134],"typically":[7],"trained":[8],"on":[9,69],"large":[10,101],"amounts":[11,102],"of":[12,20,37,46,103,145,157],"data.":[13],"In":[14,30],"many":[15],"practical":[16],"scenarios,":[17],"the":[18,35,44,75,89,98,124,139,143,155],"amount":[19],"labeled":[21],"speech":[22,39,77,108,125,130],"is":[23],"often":[24],"limited":[25],"as":[26,50],"opposed":[27],"to":[28,42,81,113,150],"text.":[29],"this":[31,72,137],"study,":[32],"we":[33,94],"investigate":[34],"use":[36],"non-parallel":[38],"and":[40,78,153],"text":[41,79,104],"improve":[43],"performance":[45,144,156],"dialog":[47],"act":[48],"recognition":[49,131],"an":[51,128],"example":[52],"SLU":[53],"task.":[54],"We":[55,119],"propose":[56],"a":[57,85],"multiview":[58],"architecture":[59],"that":[60,96,122],"can":[61],"handle":[62],"each":[63],"modality":[64],"separately.":[65],"To":[66],"effectively":[67],"train":[68],"such":[70],"data,":[71],"model":[73],"enforces":[74],"internal":[76],"encodings":[80],"be":[82],"similar":[83],"using":[84,100,158],"shared":[86],"classifier.":[87],"On":[88],"Switchboard":[90],"Dialog":[91],"Act":[92],"corpus,":[93],"show":[95,121],"pretraining":[97],"classifier":[99],"helps":[105],"learning":[106],"better":[107],"encodings,":[109],"resulting":[110],"in":[111,136],"up":[112,149],"40%":[114],"relatively":[115],"higher":[116],"classification":[117],"accuracies.":[118],"also":[120],"when":[123],"embeddings":[126],"from":[127],"automatic":[129],"(ASR)":[132],"system":[133],"used":[135],"framework,":[138],"speech-only":[140],"accuracy":[141],"exceeds":[142],"ASR-text":[146],"based":[147],"tests":[148],"15%":[151],"relative":[152],"approaches":[154],"true":[159],"transcripts.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}