{"id":"https://openalex.org/W4226302523","doi":"https://doi.org/10.21437/interspeech.2022-10800","title":"Deliberation Model for On-Device Spoken Language Understanding","display_name":"Deliberation Model for On-Device Spoken Language Understanding","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4226302523","doi":"https://doi.org/10.21437/interspeech.2022-10800"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10800","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10800","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":"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/A5085310066","display_name":"Manh Duc Le","orcid":"https://orcid.org/0000-0003-3012-6053"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duc Le","raw_affiliation_strings":["Meta, USA"],"affiliations":[{"raw_affiliation_string":"Meta, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045502911","display_name":"Akshat Shrivastava","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Akshat Shrivastava","raw_affiliation_strings":["Meta, USA"],"affiliations":[{"raw_affiliation_string":"Meta, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027043104","display_name":"Paden Tomasello","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paden D. Tomasello","raw_affiliation_strings":["Meta, USA"],"affiliations":[{"raw_affiliation_string":"Meta, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062940343","display_name":"Suyoun Kim","orcid":"https://orcid.org/0000-0002-6822-337X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suyoun Kim","raw_affiliation_strings":["Meta, USA"],"affiliations":[{"raw_affiliation_string":"Meta, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068997476","display_name":"Aleksandr Livshits","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aleksandr Livshits","raw_affiliation_strings":["Meta, USA"],"affiliations":[{"raw_affiliation_string":"Meta, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066166549","display_name":"Ozlem Kalinli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ozlem Kalinli","raw_affiliation_strings":["Meta, USA"],"affiliations":[{"raw_affiliation_string":"Meta, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041313589","display_name":"Michael L. Seltzer","orcid":"https://orcid.org/0000-0003-3474-2451"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Seltzer","raw_affiliation_strings":["Meta, USA"],"affiliations":[{"raw_affiliation_string":"Meta, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5045502911"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4155,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.55542986,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3468","last_page":"3472"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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/T12031","display_name":"Speech and dialogue systems","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":0.9995999932289124,"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":0.9994000196456909,"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":0.7464672327041626},{"id":"https://openalex.org/keywords/deliberation","display_name":"Deliberation","score":0.6833757162094116},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.6693804264068604},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5732218623161316},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46132463216781616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38623881340026855},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.06513971090316772},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.05965191125869751}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7464672327041626},{"id":"https://openalex.org/C2776946740","wikidata":"https://www.wikidata.org/wiki/Q358652","display_name":"Deliberation","level":3,"score":0.6833757162094116},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6693804264068604},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5732218623161316},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46132463216781616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38623881340026855},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.06513971090316772},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.05965191125869751},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10800","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10800","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":0.47999998927116394,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W2606974598","https://openalex.org/W2892248135","https://openalex.org/W2894164357","https://openalex.org/W2936774411","https://openalex.org/W2963250244","https://openalex.org/W2963288440","https://openalex.org/W2963979492","https://openalex.org/W2965373594","https://openalex.org/W3011339933","https://openalex.org/W3049038774","https://openalex.org/W3103469330","https://openalex.org/W3104713013","https://openalex.org/W3105218021","https://openalex.org/W3149509723","https://openalex.org/W3156849929","https://openalex.org/W3162042236","https://openalex.org/W3166029516","https://openalex.org/W3174008653","https://openalex.org/W3179843342","https://openalex.org/W3188372498","https://openalex.org/W4287240666","https://openalex.org/W4303494317","https://openalex.org/W4319862713","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2753773138","https://openalex.org/W3204354834","https://openalex.org/W6292469","https://openalex.org/W2801092833","https://openalex.org/W2901193592","https://openalex.org/W156167186","https://openalex.org/W2223796429","https://openalex.org/W2503756621","https://openalex.org/W3204019825","https://openalex.org/W633922780"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,14,26,50,157],"novel":[3],"deliberation-based":[4],"approach":[5,82,123,133],"to":[6,57,91,116,126,144,153],"end-to-end":[7],"(E2E)":[8],"spoken":[9,95],"language":[10,29],"understanding":[11,30],"(SLU),":[12],"where":[13],"streaming":[15],"automatic":[16],"speech":[17,143,146],"recognition":[18],"(ASR)":[19],"model":[20],"produces":[21],"the":[22,34,63,72,94,98,104,113,118,137],"first-pass":[23,119],"hypothesis":[24],"and":[25,43,69,108],"second-pass":[27],"natural":[28,142],"(NLU)":[31],"component":[32],"generates":[33],"semantic":[35,61],"parse":[36],"by":[37,89],"conditioning":[38],"on":[39,93],"both":[40],"ASR's":[41],"text":[42,107],"audio":[44,109],"embeddings.By":[45],"formulating":[46],"E2E":[47,163],"SLU":[48],"as":[49],"generalized":[51],"decoder,":[52],"our":[53,80,122,132],"system":[54,73],"is":[55,151],"able":[56],"support":[58],"complex":[59],"compositional":[60],"structures.Furthermore,":[62],"sharing":[64],"of":[65,97,106],"parameters":[66],"between":[67],"ASR":[68,127],"NLU":[70,87],"makes":[71,121],"especially":[74],"suitable":[75],"for":[76,160],"resource-constrained":[77],"(on-device)":[78],"environments;":[79],"proposed":[81],"consistently":[83],"outperforms":[84],"strong":[85],"pipeline":[86],"baselines":[88],"0.60%":[90],"0.65%":[92],"version":[96],"TOPv2":[99],"dataset":[100],"(STOP).We":[101],"demonstrate":[102],"that":[103,131],"fusion":[105],"features,":[110],"coupled":[111],"with":[112],"system's":[114],"ability":[115],"rewrite":[117],"hypothesis,":[120],"more":[124,149],"robust":[125],"errors.Finally,":[128],"we":[129],"show":[130],"can":[134],"significantly":[135],"reduce":[136],"degradation":[138],"when":[139],"moving":[140],"from":[141],"synthetic":[145],"training,":[147],"but":[148],"work":[150],"required":[152],"make":[154],"text-to-speech":[155],"(TTS)":[156],"viable":[158],"solution":[159],"scaling":[161],"up":[162],"SLU.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
