{"id":"https://openalex.org/W3179843342","doi":"https://doi.org/10.21437/interspeech.2021-793","title":"FANS: Fusing ASR and NLU for On-Device SLU","display_name":"FANS: Fusing ASR and NLU for On-Device SLU","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3179843342","doi":"https://doi.org/10.21437/interspeech.2021-793","mag":"3179843342"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-793","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-793","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":"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/A5023415990","display_name":"Martin Radfar","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":"Martin Radfar","raw_affiliation_strings":["Alexa Machine Learning, Amazon, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Machine Learning, Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029573067","display_name":"Athanasios Mouchtaris","orcid":"https://orcid.org/0000-0001-7583-0189"},"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":"Athanasios Mouchtaris","raw_affiliation_strings":["Alexa Machine Learning, Amazon, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Machine Learning, Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074068808","display_name":"Siegfried Kunzmann","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":"Siegfried Kunzmann","raw_affiliation_strings":["Alexa Machine Learning, Amazon, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Machine Learning, Amazon, 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":["Alexa Machine Learning, Amazon, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Machine Learning, Amazon, 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":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1224","last_page":"1228"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9957000017166138,"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":0.9957000017166138,"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":0.9933000206947327,"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":0.9927999973297119,"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":0.6619956493377686},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4222710430622101},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3341609239578247}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6619956493377686},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4222710430622101},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3341609239578247}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-793","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-793","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W14941018","https://openalex.org/W648947103","https://openalex.org/W1972595521","https://openalex.org/W1984076147","https://openalex.org/W2133564696","https://openalex.org/W2153962611","https://openalex.org/W2397579082","https://openalex.org/W2786839803","https://openalex.org/W2891229414","https://openalex.org/W2894164357","https://openalex.org/W2963230678","https://openalex.org/W2963288440","https://openalex.org/W2964052309","https://openalex.org/W3006901707","https://openalex.org/W3015412890","https://openalex.org/W3015867372","https://openalex.org/W3016006013","https://openalex.org/W3049038774","https://openalex.org/W3095552229","https://openalex.org/W3096109555","https://openalex.org/W3096251052","https://openalex.org/W3104113994","https://openalex.org/W3148001440","https://openalex.org/W3161223924","https://openalex.org/W3162875390","https://openalex.org/W4286799969","https://openalex.org/W4287659219","https://openalex.org/W4297683418","https://openalex.org/W4299350540","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W3192589309"],"abstract_inverted_index":{"Spoken":[0],"language":[1],"understanding":[2],"(SLU)":[3],"systems":[4,26],"translate":[5],"voice":[6],"input":[7,40,92],"commands":[8],"to":[9,42,74,79,140,152],"semantics":[10],"which":[11,110,137],"are":[12,111,135],"encoded":[13],"as":[14],"an":[15,70,127,173],"intent":[16,51],"and":[17,22,46,52,85,105,120,125,132,147,161,167,177,180],"pairs":[18],"of":[19,30,100,109,144],"slot":[20,83,86,118,121],"tags":[21,119],"values.Most":[23],"current":[24],"SLU":[25,66,156,175,188],"deploy":[27],"a":[28,43,63,75,90,101,186],"cascade":[29],"two":[31,108],"neural":[32,130],"models":[33],"where":[34],"the":[35,39,47,50,55,81,95,153],"first":[36],"one":[37],"maps":[38],"audio":[41,72,103],"transcript":[44,56],"(ASR)":[45],"second":[48],"predicts":[49],"slots":[53],"from":[54,89],"(NLU).In":[57],"this":[58],"paper,":[59],"we":[60],"introduce":[61],"FANS,":[62],"new":[64],"end-to-end":[65],"model":[67],"that":[68,114],"fuses":[69],"ASR":[71],"encoder":[73,104,131],"multi-task":[76],"NLU":[77],"decoder":[78],"infer":[80],"intent,":[82],"tags,":[84],"values":[87,122],"directly":[88],"given":[91],"audio,":[93],"obviating":[94],"need":[96],"for":[97],"transcription.FANS":[98],"consists":[99],"shared":[102],"three":[106],"decoders,":[107],"seq-to-seq":[112],"decoders":[113,133],"predict":[115],"non":[116],"null":[117],"in":[123,126],"parallel":[124],"auto-regressive":[128],"manner.FANS":[129],"architectures":[134],"flexible":[136],"allows":[138],"us":[139],"leverage":[141],"different":[142],"combinations":[143],"LSTM,":[145],"self-attention,":[146],"attenders.Our":[148],"experiments":[149],"show":[150],"compared":[151],"state-of-the-art":[154],"end-toend":[155],"models,":[157],"FANS":[158],"reduces":[159],"ICER":[160],"IRER":[162],"errors":[163],"relatively":[164],"by":[165,178],"30%":[166],"7%,":[168],"respectively,":[169],"when":[170,183],"tested":[171,184],"on":[172,185],"in-house":[174],"dataset":[176],"0.86%":[179],"2%":[181],"absolute":[182],"public":[187],"dataset.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}