{"id":"https://openalex.org/W3198361190","doi":"https://doi.org/10.21437/interspeech.2021-788","title":"Speak or Chat with Me: End-to-End Spoken Language Understanding System with Flexible Inputs","display_name":"Speak or Chat with Me: End-to-End Spoken Language Understanding System with Flexible Inputs","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198361190","doi":"https://doi.org/10.21437/interspeech.2021-788","mag":"3198361190"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-788","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-788","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5040366104","display_name":"Sujeong Cha","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sujeong Cha","raw_affiliation_strings":["New York University, USA"],"affiliations":[{"raw_affiliation_string":"New York University, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036021991","display_name":"Wangrui Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wangrui Hou","raw_affiliation_strings":["New York University, USA"],"affiliations":[{"raw_affiliation_string":"New York University, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040576505","display_name":"Hyun Kyoung Jung","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyun Jung","raw_affiliation_strings":["New York University, USA"],"affiliations":[{"raw_affiliation_string":"New York University, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034989625","display_name":"My Phung","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"My Phung","raw_affiliation_strings":["New York University, USA"],"affiliations":[{"raw_affiliation_string":"New York University, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034529775","display_name":"Michael Picheny","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Picheny","raw_affiliation_strings":["New York University, USA"],"affiliations":[{"raw_affiliation_string":"New York University, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110252428","display_name":"Hong-Kwang Jeff Kuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong-Kwang J. Kuo","raw_affiliation_strings":["IBM Research AI, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":["IBM Research AI, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079262240","display_name":"Edmilson Morais","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113516","display_name":"IBM Research - Brazil","ror":"https://ror.org/01fxqdx25","country_code":"BR","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210113516","https://openalex.org/I4210114115"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Edmilson Morais","raw_affiliation_strings":["IBM Research AI, Brazil"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, Brazil","institution_ids":["https://openalex.org/I4210113516"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5040366104"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":0.8158,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78329906,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4723","last_page":"4727"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9965999722480774,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9965999722480774,"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":0.9962000250816345,"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":0.9930999875068665,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.7876051664352417},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7618587017059326},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5508487224578857},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3737660050392151},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.31163346767425537},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28505682945251465}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7876051664352417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7618587017059326},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5508487224578857},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3737660050392151},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31163346767425537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28505682945251465}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-788","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-788","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310638","display_name":"McGill University","ror":"https://ror.org/01pxwe438"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W2075085977","https://openalex.org/W2149980590","https://openalex.org/W2153338568","https://openalex.org/W2158275940","https://openalex.org/W2786839803","https://openalex.org/W2891229414","https://openalex.org/W2894164357","https://openalex.org/W2896457183","https://openalex.org/W2914417638","https://openalex.org/W2963288440","https://openalex.org/W2972584841","https://openalex.org/W2980282514","https://openalex.org/W3015797571","https://openalex.org/W3016006013","https://openalex.org/W3095552229","https://openalex.org/W3174321708","https://openalex.org/W3176896803","https://openalex.org/W4287596060"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2151749779","https://openalex.org/W1999612375","https://openalex.org/W2001405890","https://openalex.org/W2159086674"],"abstract_inverted_index":{"A":[0],"major":[1],"focus":[2],"of":[3,77],"recent":[4],"research":[5],"in":[6,45,137,174],"spoken":[7],"language":[8],"understanding":[9],"(SLU)":[10],"has":[11],"been":[12],"on":[13,152,159,182],"the":[14,62,114,156],"end-to-end":[15],"approach":[16,32],"where":[17],"a":[18,67,109,119,127,138,175],"single":[19,110],"model":[20,124],"can":[21,38,71],"predict":[22,72],"intents":[23,73],"directly":[24],"from":[25,74],"speech":[26,37,50,57,94],"inputs":[27],"without":[28],"intermediate":[29],"transcripts.However,":[30],"this":[31,144],"presents":[33],"some":[34,46],"challenges.First,":[35],"since":[36],"be":[39],"considered":[40],"as":[41],"personally":[42],"identifiable":[43],"information,":[44],"cases":[47],"only":[48],"automatic":[49],"recognition":[51],"(ASR)":[52],"transcripts":[53,97],"are":[54,98],"accessible.Second,":[55],"intent-labeled":[56],"data":[58],"is":[59],"scarce.To":[60],"address":[61,113],"first":[63],"challenge,":[64,116],"we":[65,103,117],"propose":[66],"novel":[68],"system":[69,101,129,145,176],"that":[70,130,177],"flexible":[75],"types":[76],"inputs:":[78],"speech,":[79],"ASR":[80,96],"transcripts,":[81],"or":[82],"both.We":[83],"demonstrate":[84],"strong":[85],"performance":[86,181],"for":[87,167],"either":[88],"modality":[89],"separately,":[90],"and":[91,95,125,134,154,170,185],"when":[92],"both":[93],"available,":[99],"through":[100],"combination,":[102],"achieve":[104],"better":[105],"results":[106],"than":[107],"using":[108],"input":[111],"modality.To":[112],"second":[115],"leverage":[118],"semantically":[120],"robust":[121],"pre-trained":[122,151],"BERT":[123],"adopt":[126],"cross-modal":[128],"co-trains":[131],"text":[132,157],"embeddings":[133,136],"acoustic":[135,149],"shared":[139],"latent":[140],"space.We":[141],"further":[142],"enhance":[143],"by":[146],"utilizing":[147],"an":[148],"module":[150,158],"LibriSpeech":[153],"domain-adapting":[155],"our":[160],"target":[161],"datasets.Our":[162],"experiments":[163],"show":[164],"significant":[165],"advantages":[166],"these":[168],"pre-training":[169],"fine-tuning":[171],"strategies,":[172],"resulting":[173],"achieves":[178],"competitive":[179],"intent-classification":[180],"Snips":[183],"SLU":[184],"Fluent":[186],"Speech":[187],"Commands":[188],"datasets.":[189]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}