{"id":"https://openalex.org/W3015747801","doi":"https://doi.org/10.1109/icassp40776.2020.9053213","title":"Joint Contextual Modeling for ASR Correction and Language Understanding","display_name":"Joint Contextual Modeling for ASR Correction and Language Understanding","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015747801","doi":"https://doi.org/10.1109/icassp40776.2020.9053213","mag":"3015747801"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053213","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053213","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/A5113900053","display_name":"Yue Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I2946016260","display_name":"Uber AI (United States)","ror":"https://ror.org/05vm0ed18","country_code":"US","type":"company","lineage":["https://openalex.org/I2946016260"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yue Weng","raw_affiliation_strings":["Uber AI"],"affiliations":[{"raw_affiliation_string":"Uber AI","institution_ids":["https://openalex.org/I2946016260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064426728","display_name":"Sai Sumanth Miryala","orcid":null},"institutions":[{"id":"https://openalex.org/I2946016260","display_name":"Uber AI (United States)","ror":"https://ror.org/05vm0ed18","country_code":"US","type":"company","lineage":["https://openalex.org/I2946016260"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sai Sumanth Miryala","raw_affiliation_strings":["Uber AI"],"affiliations":[{"raw_affiliation_string":"Uber AI","institution_ids":["https://openalex.org/I2946016260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043744102","display_name":"Chandra Khatri","orcid":null},"institutions":[{"id":"https://openalex.org/I2946016260","display_name":"Uber AI (United States)","ror":"https://ror.org/05vm0ed18","country_code":"US","type":"company","lineage":["https://openalex.org/I2946016260"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chandra Khatri","raw_affiliation_strings":["Uber AI"],"affiliations":[{"raw_affiliation_string":"Uber AI","institution_ids":["https://openalex.org/I2946016260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100649063","display_name":"Runze Wang","orcid":"https://orcid.org/0000-0002-5429-2163"},"institutions":[{"id":"https://openalex.org/I2946016260","display_name":"Uber AI (United States)","ror":"https://ror.org/05vm0ed18","country_code":"US","type":"company","lineage":["https://openalex.org/I2946016260"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Runze Wang","raw_affiliation_strings":["Uber AI"],"affiliations":[{"raw_affiliation_string":"Uber AI","institution_ids":["https://openalex.org/I2946016260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003807260","display_name":"Huaixiu Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I2946016260","display_name":"Uber AI (United States)","ror":"https://ror.org/05vm0ed18","country_code":"US","type":"company","lineage":["https://openalex.org/I2946016260"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huaixiu Zheng","raw_affiliation_strings":["Uber AI"],"affiliations":[{"raw_affiliation_string":"Uber AI","institution_ids":["https://openalex.org/I2946016260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028406899","display_name":"Piero Molino","orcid":null},"institutions":[{"id":"https://openalex.org/I2946016260","display_name":"Uber AI (United States)","ror":"https://ror.org/05vm0ed18","country_code":"US","type":"company","lineage":["https://openalex.org/I2946016260"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piero Molino","raw_affiliation_strings":["Uber AI"],"affiliations":[{"raw_affiliation_string":"Uber AI","institution_ids":["https://openalex.org/I2946016260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026771837","display_name":"Mahdi Namazifar","orcid":null},"institutions":[{"id":"https://openalex.org/I2946016260","display_name":"Uber AI (United States)","ror":"https://ror.org/05vm0ed18","country_code":"US","type":"company","lineage":["https://openalex.org/I2946016260"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahdi Namazifar","raw_affiliation_strings":["Uber AI"],"affiliations":[{"raw_affiliation_string":"Uber AI","institution_ids":["https://openalex.org/I2946016260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014990977","display_name":"Alexandros Papangelis","orcid":null},"institutions":[{"id":"https://openalex.org/I2946016260","display_name":"Uber AI (United States)","ror":"https://ror.org/05vm0ed18","country_code":"US","type":"company","lineage":["https://openalex.org/I2946016260"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexandros Papangelis","raw_affiliation_strings":["Uber AI"],"affiliations":[{"raw_affiliation_string":"Uber AI","institution_ids":["https://openalex.org/I2946016260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010040213","display_name":"Hugh Williams","orcid":"https://orcid.org/0009-0007-5086-5319"},"institutions":[{"id":"https://openalex.org/I2946016260","display_name":"Uber AI (United States)","ror":"https://ror.org/05vm0ed18","country_code":"US","type":"company","lineage":["https://openalex.org/I2946016260"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hugh Williams","raw_affiliation_strings":["Uber AI"],"affiliations":[{"raw_affiliation_string":"Uber AI","institution_ids":["https://openalex.org/I2946016260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033560576","display_name":"Franziska Bell","orcid":null},"institutions":[{"id":"https://openalex.org/I2946016260","display_name":"Uber AI (United States)","ror":"https://ror.org/05vm0ed18","country_code":"US","type":"company","lineage":["https://openalex.org/I2946016260"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Franziska Bell","raw_affiliation_strings":["Uber AI"],"affiliations":[{"raw_affiliation_string":"Uber AI","institution_ids":["https://openalex.org/I2946016260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087941479","display_name":"G\u00f6khan T\u00fcr","orcid":null},"institutions":[{"id":"https://openalex.org/I2946016260","display_name":"Uber AI (United States)","ror":"https://ror.org/05vm0ed18","country_code":"US","type":"company","lineage":["https://openalex.org/I2946016260"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gokhan Tur","raw_affiliation_strings":["Uber AI"],"affiliations":[{"raw_affiliation_string":"Uber AI","institution_ids":["https://openalex.org/I2946016260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5113900053"],"corresponding_institution_ids":["https://openalex.org/I2946016260"],"apc_list":null,"apc_paid":null,"fwci":5.0373,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.96052502,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6349","last_page":"6353"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.8770056962966919},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7924515604972839},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5876001715660095},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5864723920822144},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5189914107322693},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5149105787277222},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5088756084442139},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49052685499191284},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.458626925945282},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43473032116889954},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4220428168773651},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3160933554172516}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8770056962966919},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7924515604972839},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5876001715660095},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5864723920822144},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5189914107322693},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5149105787277222},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5088756084442139},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49052685499191284},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.458626925945282},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43473032116889954},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4220428168773651},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3160933554172516},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053213","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053213","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":[{"id":"https://metadata.un.org/sdg/10","score":0.6399999856948853,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W55328212","https://openalex.org/W648947103","https://openalex.org/W1571931074","https://openalex.org/W1649407914","https://openalex.org/W1940872118","https://openalex.org/W2035438624","https://openalex.org/W2113563392","https://openalex.org/W2124445791","https://openalex.org/W2137871902","https://openalex.org/W2166293310","https://openalex.org/W2251058040","https://openalex.org/W2321916036","https://openalex.org/W2399456070","https://openalex.org/W2400801499","https://openalex.org/W2473329891","https://openalex.org/W2473965551","https://openalex.org/W2507756961","https://openalex.org/W2511962886","https://openalex.org/W2762590475","https://openalex.org/W2810084418","https://openalex.org/W2888936194","https://openalex.org/W2894164357","https://openalex.org/W2896094646","https://openalex.org/W2896457183","https://openalex.org/W2916997151","https://openalex.org/W2917128112","https://openalex.org/W2962739339","https://openalex.org/W2963045354","https://openalex.org/W2963341956","https://openalex.org/W2963660642","https://openalex.org/W2963756346","https://openalex.org/W2963974889","https://openalex.org/W2964117975","https://openalex.org/W4302343710","https://openalex.org/W6602256816","https://openalex.org/W6640362995","https://openalex.org/W6700656258","https://openalex.org/W6712249138","https://openalex.org/W6713001283","https://openalex.org/W6721195979","https://openalex.org/W6725207838","https://openalex.org/W6742080785","https://openalex.org/W6745501496","https://openalex.org/W6746515341","https://openalex.org/W6748148878","https://openalex.org/W6755126687","https://openalex.org/W6755207826","https://openalex.org/W6759393636"],"related_works":["https://openalex.org/W2495256954","https://openalex.org/W2259317772","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W2944691285","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W26527944"],"abstract_inverted_index":{"The":[0],"quality":[1],"of":[2,50,58,199,222],"automatic":[3],"speech":[4],"recognition":[5],"(ASR)":[6],"is":[7],"critical":[8],"to":[9,16,35,46,93,103,125,138,156],"Dialogue":[10,68],"Systems":[11],"as":[12,23],"ASR":[13,41,97,143,166,203],"errors":[14],"propagate":[15],"and":[17,85,108,118,145,151,169,204],"directly":[18],"impact":[19],"downstream":[20],"tasks":[21,52],"such":[22],"language":[24,38],"understanding":[25],"(LU).":[26],"In":[27],"this":[28,59],"paper,":[29],"we":[30,61,77],"propose":[31],"multi-task":[32],"neural":[33],"approaches":[34],"perform":[36],"contextual":[37],"correction":[39,168],"on":[40,182],"outputs":[42],"jointly":[43],"with":[44,122,178,215],"LU":[45,170,206],"improve":[47],"the":[48,56,66,95,105,127,141,148,186,191,196,201],"performance":[49],"both":[51],"simultaneously.":[53],"To":[54],"measure":[55],"effectiveness":[57],"approach":[60],"used":[62],"a":[63,74,101,163,172],"public":[64],"benchmark,":[65],"2nd":[67],"State":[69],"Tracking":[70],"(DSTC2)":[71],"corpus.":[72],"As":[73],"baseline":[75],"approach,":[76],"trained":[78,113,218],"task":[79],"specific":[80],"Statistical":[81],"Language":[82,91],"Models":[83],"(SLM)":[84],"fine-tuned":[86],"state-of-the-art":[87],"Generative":[88],"Pre-training":[89],"(GPT)":[90],"Model":[92],"re-rank":[94],"n-best":[96,131],"hypotheses,":[98],"followed":[99],"by":[100,212],"model":[102],"identify":[104,147],"dialog":[106],"act":[107,150],"slots.":[109],"i)":[110],"We":[111,133,160,193],"further":[112],"ranker":[114,136],"models":[115,121,137,217],"using":[116,219],"GPT":[117],"Hierarchical":[119],"CNN-RNN":[120],"discriminatory":[123],"losses":[124],"detect":[126],"best":[128,142],"output":[129,144],"given":[130],"hypotheses.":[132],"extended":[134],"these":[135],"first":[139],"select":[140],"then":[146],"dialogue":[149],"slots":[152],"in":[153],"an":[154],"end":[155,157],"fashion.":[158],"ii)":[159],"also":[161],"proposed":[162],"novel":[164],"joint":[165,216],"error":[167,197],"model,":[171],"word":[173,187],"confusion":[174],"pointer":[175],"network":[176],"(WCN-Ptr)":[177],"multihead":[179],"self":[180],"attention":[181],"top,":[183],"which":[184],"consumes":[185],"confusions":[188],"populated":[189],"from":[190],"n-best.":[192],"show":[194],"that":[195],"rates":[198],"off":[200],"shelf":[202],"following":[205],"systems":[207],"can":[208],"be":[209],"reduced":[210],"significantly":[211],"14%":[213],"relative":[214],"small":[220],"amounts":[221],"in-domain":[223],"data.":[224]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}