{"id":"https://openalex.org/W2787948962","doi":"https://doi.org/10.1109/icassp.2018.8461785","title":"Towards End-to-end Spoken Language Understanding","display_name":"Towards End-to-end Spoken Language Understanding","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2787948962","doi":"https://doi.org/10.1109/icassp.2018.8461785","mag":"2787948962"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461785","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/1802.08395","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023556869","display_name":"Dmitriy Serdyuk","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dmitriy Serdyuk","raw_affiliation_strings":["Facebook One Hacker Way Menlo Park, CA, USA","Facebook One Hacker Way Menlo Park, CA, 94025, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook One Hacker Way Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook One Hacker Way Menlo Park, CA, 94025, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339989","display_name":"Yongqiang Wang","orcid":"https://orcid.org/0000-0002-8600-0276"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yongqiang Wang","raw_affiliation_strings":["Facebook One Hacker Way Menlo Park, CA, USA","Facebook One Hacker Way Menlo Park, CA, 94025, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook One Hacker Way Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook One Hacker Way Menlo Park, CA, 94025, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047073253","display_name":"Christian Fuegen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christian Fuegen","raw_affiliation_strings":["Facebook One Hacker Way Menlo Park, CA, USA","Facebook One Hacker Way Menlo Park, CA, 94025, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook One Hacker Way Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook One Hacker Way Menlo Park, CA, 94025, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052627610","display_name":"Anuj Kumar","orcid":"https://orcid.org/0000-0001-8803-152X"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anuj Kumar","raw_affiliation_strings":["Facebook One Hacker Way Menlo Park, CA, USA","Facebook One Hacker Way Menlo Park, CA, 94025, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook One Hacker Way Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook One Hacker Way Menlo Park, CA, 94025, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101733763","display_name":"Baiyang Liu","orcid":"https://orcid.org/0000-0002-8672-5146"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baiyang Liu","raw_affiliation_strings":["Facebook One Hacker Way Menlo Park, CA, USA","Facebook One Hacker Way Menlo Park, CA, 94025, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook One Hacker Way Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook One Hacker Way Menlo Park, CA, 94025, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086198262","display_name":"Yoshua Bengio","orcid":"https://orcid.org/0000-0002-9322-3515"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yoshua Bengio","raw_affiliation_strings":["Facebook One Hacker Way Menlo Park, CA, USA","Facebook One Hacker Way Menlo Park, CA, 94025, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook One Hacker Way Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook One Hacker Way Menlo Park, CA, 94025, USA","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5343,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.91622534,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5754","last_page":"5758"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994999766349792,"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":0.8471413254737854},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6705823540687561},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6384444236755371},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.6266352534294128},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.5861532092094421},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.550664484500885},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.5496467351913452},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5432980060577393},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5312839150428772},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5291638374328613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5246734023094177},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.45935654640197754},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4310159981250763},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42930343747138977},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4177195727825165},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.4107731282711029},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.26398056745529175},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.23908501863479614},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18739303946495056},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.1726982593536377},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07924529910087585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8471413254737854},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6705823540687561},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6384444236755371},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6266352534294128},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.5861532092094421},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.550664484500885},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.5496467351913452},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5432980060577393},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5312839150428772},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5291638374328613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5246734023094177},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.45935654640197754},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4310159981250763},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42930343747138977},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4177195727825165},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.4107731282711029},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26398056745529175},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.23908501863479614},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18739303946495056},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.1726982593536377},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07924529910087585},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2018.8461785","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1802.08395","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.08395","pdf_url":"https://arxiv.org/pdf/1802.08395","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":"","raw_type":null},{"id":"mag:2787948962","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1802.08395","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.1802.08395","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1802.08395","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1802.08395","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.08395","pdf_url":"https://arxiv.org/pdf/1802.08395","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":"","raw_type":null},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2787948962.pdf","grobid_xml":"https://content.openalex.org/works/W2787948962.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W648947103","https://openalex.org/W1522301498","https://openalex.org/W1649407914","https://openalex.org/W1828163288","https://openalex.org/W1924770834","https://openalex.org/W1964812476","https://openalex.org/W2064675550","https://openalex.org/W2265846598","https://openalex.org/W2293634267","https://openalex.org/W2400801499","https://openalex.org/W2473965551","https://openalex.org/W2613904329","https://openalex.org/W2739427748","https://openalex.org/W2949117887","https://openalex.org/W2949382160","https://openalex.org/W2949888546","https://openalex.org/W2951327905","https://openalex.org/W2964308564","https://openalex.org/W6623517193","https://openalex.org/W6630875275","https://openalex.org/W6643290180","https://openalex.org/W6651570682","https://openalex.org/W6659354092","https://openalex.org/W6669997747","https://openalex.org/W6676220427","https://openalex.org/W6676562027","https://openalex.org/W6679436768","https://openalex.org/W6683738474","https://openalex.org/W6687566353","https://openalex.org/W6696934422","https://openalex.org/W6702097088","https://openalex.org/W6713001283","https://openalex.org/W6713452507"],"related_works":["https://openalex.org/W2963288440","https://openalex.org/W2949079242","https://openalex.org/W2155448060","https://openalex.org/W2008955157","https://openalex.org/W2972525948","https://openalex.org/W3174321708","https://openalex.org/W2157351094","https://openalex.org/W2091502948","https://openalex.org/W3188372498","https://openalex.org/W2582895315","https://openalex.org/W2096192176","https://openalex.org/W3169666445","https://openalex.org/W2938973646","https://openalex.org/W3093529776","https://openalex.org/W2949261431","https://openalex.org/W2891229414","https://openalex.org/W183684959","https://openalex.org/W1972595521","https://openalex.org/W1556528841","https://openalex.org/W2886025712"],"abstract_inverted_index":{"Spoken":[0],"language":[1,37,82],"understanding":[2,38],"system":[3,39,79],"is":[4,19],"traditionally":[5],"designed":[6],"as":[7,46,55],"a":[8,11,35],"pipeline":[9],"of":[10,13],"number":[12],"components.":[14],"First,":[15],"the":[16,32,41,91,99,107,118,122,127],"audio":[17,96,128],"signal":[18],"processed":[20],"by":[21],"an":[22,76],"automatic":[23],"speech":[24],"recognizer":[25],"for":[26,51,80],"transcription":[27],"or":[28],"n-best":[29],"hypotheses.":[30],"With":[31,84],"recognition":[33],"results,":[34],"natural":[36],"classifies":[40],"text":[42,101],"to":[43],"structured":[44],"data":[45],"domain,":[47],"intent":[48],"and":[49,65,115],"slots":[50],"down-streaming":[52],"consumers,":[53],"such":[54],"dialog":[56],"system,":[57],"hands-free":[58],"applications.":[59],"These":[60],"components":[61],"are":[62],"usually":[63],"developed":[64],"optimized":[66],"independently.":[67],"In":[68],"this":[69,85],"paper,":[70],"we":[71,88],"present":[72],"our":[73],"study":[74,104],"on":[75],"end-to-end":[77],"learning":[78],"spoken":[81],"understanding.":[83],"unified":[86],"approach,":[87],"can":[89,110,120],"infer":[90],"semantic":[92,123],"meaning":[93],"directly":[94,125],"from":[95,126],"features":[97],"without":[98],"intermediate":[100],"representation.":[102],"This":[103],"showed":[105],"that":[106,117],"trained":[108],"model":[109,119],"achieve":[111],"reasonable":[112],"good":[113],"result":[114],"demonstrated":[116],"capture":[121],"attention":[124],"features.":[129]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
