{"id":"https://openalex.org/W3161801451","doi":"https://doi.org/10.21437/interspeech.2021-836","title":"Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End","display_name":"Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3161801451","doi":"https://doi.org/10.21437/interspeech.2021-836","mag":"3161801451"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-836","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-836","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.07071","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032932928","display_name":"Swayambhu Nath Ray","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":true,"raw_author_name":"Swayambhu Nath Ray","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060740546","display_name":"Minhua Wu","orcid":"https://orcid.org/0000-0001-9798-2984"},"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":"Minhua Wu","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","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 (United States), Seattle, United States"],"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029777844","display_name":"Pegah Ghahremani","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pegah Ghahremani","raw_affiliation_strings":["Johns Hopkins University, Baltimore, United States"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, United States","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059221392","display_name":"Raghavendra Bilgi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Raghavendra Bilgi","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031236216","display_name":"Milind Rao","orcid":"https://orcid.org/0000-0003-2649-3205"},"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 (United States), Seattle, United States"],"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080360704","display_name":"Harish Arsikere","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":"Harish Arsikere","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","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 (United States), Seattle, United States"],"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"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":"Andreas Stolcke","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012153296","display_name":"Jasha Droppo","orcid":"https://orcid.org/0000-0001-6097-0090"},"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":"Jasha Droppo","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5032932928"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.28,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62341859,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3455","last_page":"3459"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/utterance","display_name":"Utterance","score":0.832267165184021},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8055763244628906},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.757855236530304},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6072849631309509},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5891862511634827},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5765496492385864},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.553970217704773},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.48752281069755554},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4476446807384491},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4275752604007721},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4224567115306854},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.40009361505508423},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3918737769126892},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07120820879936218}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.832267165184021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8055763244628906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.757855236530304},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6072849631309509},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5891862511634827},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5765496492385864},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.553970217704773},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.48752281069755554},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4476446807384491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4275752604007721},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4224567115306854},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.40009361505508423},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3918737769126892},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07120820879936218},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-836","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-836","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"},{"id":"pmh:oai:arXiv.org:2105.07071","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.07071","pdf_url":"https://arxiv.org/pdf/2105.07071","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3161801451","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2105.07071.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2105.07071","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2105.07071","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.07071","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.07071","pdf_url":"https://arxiv.org/pdf/2105.07071","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1828163288","https://openalex.org/W2127141656","https://openalex.org/W2160815625","https://openalex.org/W2327501763","https://openalex.org/W2515439472","https://openalex.org/W2786839803","https://openalex.org/W2891229414","https://openalex.org/W2894164357","https://openalex.org/W2896060389","https://openalex.org/W2928075308","https://openalex.org/W2936774411","https://openalex.org/W2962760690","https://openalex.org/W2963288440","https://openalex.org/W2963626743","https://openalex.org/W2964308564","https://openalex.org/W2970611152","https://openalex.org/W3007227084","https://openalex.org/W3015686596","https://openalex.org/W3015760975","https://openalex.org/W3024231486","https://openalex.org/W3045726014","https://openalex.org/W3049038774","https://openalex.org/W3161631007","https://openalex.org/W3166193157"],"related_works":["https://openalex.org/W3197900814","https://openalex.org/W3016006013","https://openalex.org/W3032901281","https://openalex.org/W2937649809","https://openalex.org/W3156915121","https://openalex.org/W2573660649","https://openalex.org/W1947686661","https://openalex.org/W3017862536","https://openalex.org/W3034461631","https://openalex.org/W3156762052","https://openalex.org/W2950548836","https://openalex.org/W2089234697","https://openalex.org/W2903250132","https://openalex.org/W3009565979","https://openalex.org/W3133439430","https://openalex.org/W3200945580","https://openalex.org/W2886319145","https://openalex.org/W2963739817","https://openalex.org/W2912937645","https://openalex.org/W2913851961"],"abstract_inverted_index":{"Comprehending":[0],"the":[1,11,25,53,56,59,91,102,114,127,141,155],"overall":[2],"intent":[3,30,54,97,135],"of":[4,24,27,55,61,154],"an":[5],"utterance":[6,57,104],"helps":[7],"a":[8,21,37,79,118,130,146],"listener":[9],"recognize":[10],"individual":[12],"words":[13],"spoken.":[14],"Inspired":[15],"by":[16],"this":[17,85],"fact,":[18],"we":[19],"perform":[20],"novel":[22],"study":[23,86],"impact":[26],"explicitly":[28],"incorporating":[29],"representations":[31],"as":[32,69,137],"additional":[33],"information":[34],"to":[35,108],"improve":[36],"recurrent":[38],"neural":[39],"network-transducer":[40],"(RNN-T)":[41],"based":[42],"automatic":[43],"speech":[44,83],"recognition":[45],"(ASR)":[46],"system.":[47],"An":[48],"audio-to-intent":[49],"(A2I)":[50],"model":[51],"encodes":[52],"in":[58,93],"form":[60],"embeddings":[62],"or":[63],"posteriors,":[64],"and":[65,75,105],"these":[66],"are":[67],"used":[68,107],"auxiliary":[70],"inputs":[71,139],"for":[72,140],"RNN-T":[73,111,142],"training":[74],"inference.":[76],"Experimenting":[77],"with":[78],"50k-hour":[80],"far-field":[81],"English":[82],"corpus,":[84],"shows":[87],"that":[88,159],"when":[89],"running":[90],"system":[92,132,144,157],"non-streaming":[94],"mode,":[95],"where":[96],"representation":[98],"is":[99],"extracted":[100],"from":[101,113],"entire":[103],"then":[106],"bias":[109],"streaming":[110,131,156],"search":[112],"start,":[115],"it":[116],"provides":[117],"5.56%":[119],"relative":[120,148,173],"word":[121],"error":[122],"rate":[123],"reduction":[124],"(WERR).":[125],"On":[126],"other":[128],"hand,":[129],"using":[133],"per-frame":[134],"posteriors":[136],"extra":[138],"ASR":[143],"yields":[145],"3.33%":[147],"WERR.":[149],"A":[150],"further":[151],"detailed":[152],"analysis":[153],"indicates":[158],"our":[160],"proposed":[161],"method":[162],"brings":[163],"especially":[164],"good":[165],"gain":[166],"on":[167,175],"media-playing":[168],"related":[169],"intents":[170],"(e.g.":[171],"9.12%":[172],"WERR":[174],"PlayMusicIntent).":[176]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}