{"id":"https://openalex.org/W3016006013","doi":"https://doi.org/10.1109/icassp40776.2020.9053281","title":"Leveraging Unpaired Text Data for Training End-To-End Speech-to-Intent Systems","display_name":"Leveraging Unpaired Text Data for Training End-To-End Speech-to-Intent Systems","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016006013","doi":"https://doi.org/10.1109/icassp40776.2020.9053281","mag":"3016006013"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053281","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053281","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":"conference-paper","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/A5101673889","display_name":"Yinghui Huang","orcid":"https://orcid.org/0000-0003-0607-1507"},"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":"Yinghui Huang","raw_affiliation_strings":["IBM Research AI, Yorktown Heights, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110252428","display_name":"Hong-Kwang Jeff Kuo","orcid":null},"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":"Hong-Kwang Kuo","raw_affiliation_strings":["IBM Research AI, Yorktown Heights, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"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, Yorktown Heights, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054462082","display_name":"Zvi Kons","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Zvi Kons","raw_affiliation_strings":["IBM Research AI, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015927589","display_name":"Kartik Audhkhasi","orcid":"https://orcid.org/0000-0002-2340-1144"},"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":"Kartik Audhkhasi","raw_affiliation_strings":["IBM Research AI, Yorktown Heights, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"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":"Brian Kingsbury","raw_affiliation_strings":["IBM Research AI, Yorktown Heights, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053864983","display_name":"Ron Hoory","orcid":"https://orcid.org/0009-0006-1327-5160"},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ron Hoory","raw_affiliation_strings":["IBM Research AI, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034529775","display_name":"Michael Picheny","orcid":null},"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":"Michael Picheny","raw_affiliation_strings":["IBM Research AI, Yorktown Heights, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7984","last_page":"7988"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9980000257492065,"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":0.8247238397598267},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7867534160614014},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.7347210645675659},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6489314436912537},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5968552231788635},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5381022691726685},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5048142075538635},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4828370213508606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4759613871574402},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4612411856651306},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.44762536883354187},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41738975048065186},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.41577309370040894},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.33643367886543274}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8247238397598267},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7867534160614014},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7347210645675659},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6489314436912537},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5968552231788635},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5381022691726685},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5048142075538635},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4828370213508606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4759613871574402},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4612411856651306},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.44762536883354187},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41738975048065186},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.41577309370040894},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33643367886543274},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053281","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053281","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":0.7300000190734863,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1523385540","https://openalex.org/W1883346539","https://openalex.org/W2127141656","https://openalex.org/W2149980590","https://openalex.org/W2153338568","https://openalex.org/W2184188583","https://openalex.org/W2527729766","https://openalex.org/W2786839803","https://openalex.org/W2796315435","https://openalex.org/W2891229414","https://openalex.org/W2894164357","https://openalex.org/W2896457183","https://openalex.org/W2914417638","https://openalex.org/W2936774411","https://openalex.org/W2937780860","https://openalex.org/W2944440087","https://openalex.org/W2963091184","https://openalex.org/W2963288440","https://openalex.org/W2963341956","https://openalex.org/W2963902314","https://openalex.org/W2972314145","https://openalex.org/W2972327934","https://openalex.org/W2972359262","https://openalex.org/W2972525948","https://openalex.org/W2972574864","https://openalex.org/W2972584841","https://openalex.org/W2973040747","https://openalex.org/W2973229104","https://openalex.org/W2979826702","https://openalex.org/W6631216910","https://openalex.org/W6639103823","https://openalex.org/W6686207219","https://openalex.org/W6750651883","https://openalex.org/W6755077353","https://openalex.org/W6755207826","https://openalex.org/W6769243733","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W2916997151","https://openalex.org/W3198455051","https://openalex.org/W2949174760","https://openalex.org/W4312364074","https://openalex.org/W642007152","https://openalex.org/W2341426843","https://openalex.org/W1911859126","https://openalex.org/W2131711534","https://openalex.org/W2749784707","https://openalex.org/W4387712795"],"abstract_inverted_index":{"Training":[0],"an":[1,35],"end-to-end":[2],"(E2E)":[3],"neural":[4],"network":[5],"speech-to-intent":[6,151],"(S2I)":[7],"system":[8,62],"that":[9,63],"directly":[10],"extracts":[11],"intents":[12],"from":[13],"speech":[14,20,41,82],"requires":[15],"large":[16],"amounts":[17,80],"of":[18,67,81,91,163],"intent-labeled":[19,170],"data,":[21],"which":[22,126,144],"is":[23,95,148],"time":[24],"consuming":[25],"and":[26,83,139],"expensive":[27],"to":[28,52,117,134,167],"collect.":[29],"Initializing":[30],"the":[31,65,92,119,145],"S2I":[32,61,120],"model":[33,37],"with":[34,78],"ASR":[36],"trained":[38],"on":[39],"copious":[40],"data":[42,45,94,109,141,147,152],"can":[43],"alleviate":[44],"sparsity.":[46],"In":[47],"this":[48],"paper,":[49],"we":[50,105,113],"attempt":[51],"leverage":[53],"NLU":[54],"text":[55,84,137],"resources.":[56],"We":[57,74],"implemented":[58],"a":[59,68,89,154],"CTC-based":[60],"matches":[64],"performance":[66,164],"state-of-the-art,":[69],"traditional":[70],"cascaded":[71],"SLU":[72],"system.":[73,157],"performed":[75],"controlled":[76],"experiments":[77],"varying":[79],"training":[85],"data.":[86],"When":[87],"only":[88],"tenth":[90],"original":[93],"available,":[96,112],"intent":[97,130],"classification":[98,131],"accuracy":[99],"degrades":[100],"by":[101],"7.6%":[102],"absolute.":[103],"Assuming":[104],"have":[106],"additional":[107],"text-to-intent":[108,146],"(without":[110],"speech)":[111],"investigated":[114],"two":[115],"techniques":[116],"improve":[118],"system:":[121],"(1)":[122],"transfer":[123],"learning,":[124],"in":[125,143],"acoustic":[127],"embeddings":[128],"for":[129],"are":[132],"tied":[133],"fine-tuned":[135],"BERT":[136],"embeddings;":[138],"(2)":[140],"augmentation,":[142],"converted":[149],"into":[150],"using":[153,168],"multi-speaker":[155],"text-to-speech":[156],"The":[158],"proposed":[159],"approaches":[160],"recover":[161],"80%":[162],"lost":[165],"due":[166],"limited":[169],"speech.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}