{"id":"https://openalex.org/W3049038774","doi":"https://doi.org/10.21437/interspeech.2020-2976","title":"Speech to Semantics: Improve ASR and NLU Jointly via All-Neural Interfaces","display_name":"Speech to Semantics: Improve ASR and NLU Jointly via All-Neural Interfaces","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3049038774","doi":"https://doi.org/10.21437/interspeech.2020-2976","mag":"3049038774"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2976","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2976","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.06173","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102902212","display_name":"Milind Rao","orcid":"https://orcid.org/0000-0002-6942-7833"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Milind Rao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109046112","display_name":"Anirudh Raju","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anirudh Raju","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076504502","display_name":"Pranav Dheram","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pranav Dheram","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001222583","display_name":"Bach Bui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bach Bui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5110230355","display_name":"Ariya Rastrow","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ariya Rastrow","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102902212"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2419,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.95140377,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"876","last_page":"880"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8631426095962524},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.7945045232772827},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7424667477607727},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5786063075065613},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5284823179244995},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5218759775161743},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.44719505310058594},{"id":"https://openalex.org/keywords/semantic-interpretation","display_name":"Semantic interpretation","score":0.44179412722587585},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.4304949939250946},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.42917633056640625},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42539799213409424},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4122805595397949},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39893046021461487},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3825596868991852}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8631426095962524},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.7945045232772827},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7424667477607727},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5786063075065613},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5284823179244995},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5218759775161743},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.44719505310058594},{"id":"https://openalex.org/C193125573","wikidata":"https://www.wikidata.org/wiki/Q7449065","display_name":"Semantic interpretation","level":2,"score":0.44179412722587585},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.4304949939250946},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.42917633056640625},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42539799213409424},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4122805595397949},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39893046021461487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3825596868991852},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-2976","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2976","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.06173","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.06173","pdf_url":"https://arxiv.org/pdf/2008.06173","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.06173","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.06173","pdf_url":"https://arxiv.org/pdf/2008.06173","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":[{"display_name":"Quality Education","score":0.75,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W55328212","https://openalex.org/W1828163288","https://openalex.org/W1989996186","https://openalex.org/W2007261869","https://openalex.org/W2127141656","https://openalex.org/W2296283641","https://openalex.org/W2327501763","https://openalex.org/W2750499125","https://openalex.org/W2787045460","https://openalex.org/W2894164357","https://openalex.org/W2914417638","https://openalex.org/W2936774411","https://openalex.org/W2962715022","https://openalex.org/W2962826786","https://openalex.org/W2963250244","https://openalex.org/W2963288440","https://openalex.org/W2963979492"],"related_works":["https://openalex.org/W3156493709","https://openalex.org/W4230258867","https://openalex.org/W2937725239","https://openalex.org/W3174008653","https://openalex.org/W2098498104","https://openalex.org/W2967045987","https://openalex.org/W2987457280","https://openalex.org/W3138431698","https://openalex.org/W4205560368","https://openalex.org/W1575088060"],"abstract_inverted_index":{"We":[0,86,101,166],"consider":[1],"the":[2,60,109,112,169,194],"problem":[3],"of":[4,9,141,156],"spoken":[5],"language":[6,12,43],"understanding":[7,44],"(SLU)":[8],"extracting":[10],"natural":[11,42],"intents":[13],"and":[14,118,143,182],"associated":[15],"slot":[16],"arguments":[17],"or":[18],"named":[19],"entities":[20],"from":[21,95,180],"speech":[22,36,96],"that":[23,90,158,168],"is":[24],"primarily":[25],"directed":[26],"at":[27],"voice":[28,71],"assistants.":[29],"Such":[30],"a":[31,55,77,104,123,133,150],"system":[32,117],"subsumes":[33],"both":[34],"automatic":[35],"recognition":[37],"(ASR)":[38],"as":[39,41,161,163],"well":[40,162],"(NLU).":[45],"An":[46],"end-to-end":[47,136],"joint":[48,137],"SLU":[49,138],"model":[50,172],"can":[51],"be":[52],"built":[53],"to":[54,62,73,132,175,189],"required":[56],"specification":[57],"opening":[58],"up":[59],"opportunity":[61],"deploy":[63],"on":[64],"hardware":[65],"constrained":[66],"scenarios":[67],"like":[68],"devices":[69],"enabling":[70],"assistants":[72],"work":[74],"offline,":[75],"in":[76,193],"privacy":[78],"preserving":[79],"manner,":[80],"whilst":[81],"also":[82,183],"reducing":[83],"server":[84],"costs.":[85],"first":[87],"present":[88,103],"models":[89],"extract":[91],"utterance":[92],"intent":[93],"directly":[94],"without":[97],"intermediate":[98],"text":[99],"output.":[100],"then":[102,119],"compositional":[105],"model,":[106,139],"which":[107,146],"generates":[108],"transcript":[110],"using":[111,122],"Listen":[113],"Attend":[114],"Spell":[115],"ASR":[116,142,176,190],"extracts":[120],"interpretation":[121],"neural":[124,151],"NLU":[125,144,164,181,185],"model.":[126],"Finally,":[127],"we":[128],"contrast":[129],"these":[130],"methods":[131],"jointly":[134,170],"trained":[135,171],"consisting":[140],"subsystems":[145],"are":[147],"connected":[148],"by":[149,186],"network":[152],"based":[153],"interface":[154],"instead":[155],"text,":[157],"produces":[159],"transcripts":[160],"interpretation.":[165],"show":[167],"shows":[173],"improvements":[174],"incorporating":[177],"semantic":[178],"information":[179],"improves":[184],"exposing":[187],"it":[188],"confusion":[191],"encoded":[192],"hidden":[195],"layer.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}