{"id":"https://openalex.org/W4296070421","doi":"https://doi.org/10.21437/interspeech.2022-11067","title":"On joint training with interfaces for spoken language understanding","display_name":"On joint training with interfaces for spoken language understanding","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296070421","doi":"https://doi.org/10.21437/interspeech.2022-11067"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11067","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11067","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5109046112","display_name":"Anirudh Raju","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anirudh Raju","raw_affiliation_strings":["Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113050800","display_name":"Milind Rao","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Milind Rao","raw_affiliation_strings":["Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003334789","display_name":"Gautam Tiwari","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gautam Tiwari","raw_affiliation_strings":["Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031451770","display_name":"PRANAV DHERAM","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"PRANAV DHERAM","raw_affiliation_strings":["Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105783546","display_name":"Bryan Anderson","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryan Anderson","raw_affiliation_strings":["Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443053","display_name":"Zhe Zhang","orcid":"https://orcid.org/0009-0000-0298-5497"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Zhang","raw_affiliation_strings":["Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056081738","display_name":"Chul Lee","orcid":"https://orcid.org/0000-0001-9329-7365"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chul Lee","raw_affiliation_strings":["Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114121342","display_name":"Bach Bui","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bach Bui","raw_affiliation_strings":["Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110230355","display_name":"Ariya Rastrow","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ariya Rastrow","raw_affiliation_strings":["Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":1.5182,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.85225406,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1253","last_page":"1257"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9940999746322632,"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":0.9940999746322632,"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":0.9879000186920166,"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":0.9218999743461609,"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":0.7763026356697083},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.7715855836868286},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5405162572860718},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5318538546562195},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4400067627429962},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4360792934894562},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3720512390136719},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.368047833442688},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0913017988204956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7763026356697083},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7715855836868286},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5405162572860718},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5318538546562195},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4400067627429962},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4360792934894562},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3720512390136719},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.368047833442688},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0913017988204956},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-11067","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11067","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W1971034924","https://openalex.org/W2007261869","https://openalex.org/W2131342762","https://openalex.org/W2133564696","https://openalex.org/W2137871902","https://openalex.org/W2143612262","https://openalex.org/W2327501763","https://openalex.org/W2894164357","https://openalex.org/W2896457183","https://openalex.org/W2917128112","https://openalex.org/W2963747784","https://openalex.org/W2963979492","https://openalex.org/W2972584841","https://openalex.org/W2980282514","https://openalex.org/W3006901707","https://openalex.org/W3015194534","https://openalex.org/W3016010032","https://openalex.org/W3049038774","https://openalex.org/W3094979069","https://openalex.org/W3100460087","https://openalex.org/W3110740243","https://openalex.org/W3148338017","https://openalex.org/W3161631007","https://openalex.org/W3162313915","https://openalex.org/W3174321708","https://openalex.org/W3197900814","https://openalex.org/W4230563027","https://openalex.org/W4285217170","https://openalex.org/W4287210743","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W1530808388","https://openalex.org/W4366179611","https://openalex.org/W2159086674"],"abstract_inverted_index":{"Spoken":[0],"language":[1,45,77],"understanding":[2,46],"(SLU)":[3],"systems":[4,20,51],"extract":[5],"both":[6,112],"text":[7,55,106],"transcripts":[8],"and":[9,14,41,98,108],"semantics":[10],"associated":[11],"with":[12,151],"intents":[13],"slots":[15],"from":[16,39,63],"input":[17],"speech":[18,27],"utterances.SLU":[19],"usually":[21],"consist":[22],"of":[23,147],"(1)":[24],"an":[25,32],"automatic":[26],"recognition":[28],"(ASR)":[29],"module,":[30],"(2)":[31],"interface":[33],"module":[34],"that":[35,101],"exposes":[36],"relevant":[37],"outputs":[38],"ASR,":[40],"(3)":[42],"a":[43,105,115,132],"natural":[44],"(NLU)":[47],"module.Interfaces":[48],"in":[49],"SLU":[50],"carry":[52],"information":[53,59],"on":[54,85],"transcriptions":[56],"or":[57],"richer":[58,138],"like":[60],"neural":[61,139],"embeddings":[62],"ASR":[64,97],"to":[65],"NLU.In":[66],"this":[67],"paper,":[68],"we":[69,80,141],"study":[70],"how":[71],"interfaces":[72],"affect":[73],"joint-training":[74],"for":[75],"spoken":[76],"understanding.Most":[78],"notably,":[79],"obtain":[81],"the":[82,86,126,143],"state-of-theart":[83],"results":[84,128],"publicly":[87],"available":[88],"50-hr":[89],"SLURP":[90],"[1]":[91],"dataset.We":[92],"first":[93],"leverage":[94],"large-size":[95],"pretrained":[96,121,149],"NLU":[99],"models":[100,113,122,150],"are":[102,123,129],"connected":[103],"by":[104],"interface,":[107],"then":[109],"jointly":[110],"train":[111],"via":[114],"sequence":[116,134],"loss":[117,135],"function.For":[118],"scenarios":[119],"where":[120],"not":[124],"utilized,":[125],"best":[127],"obtained":[130],"through":[131],"joint":[133],"training":[136,153],"using":[137],"interfaces.Finally,":[140],"show":[142],"overall":[144],"diminishing":[145],"impact":[146],"leveraging":[148],"increased":[152],"data":[154],"size.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
