{"id":"https://openalex.org/W3080993257","doi":"https://doi.org/10.21437/interspeech.2020-1963","title":"End-to-End Neural Transformer Based Spoken Language Understanding","display_name":"End-to-End Neural Transformer Based Spoken Language Understanding","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3080993257","doi":"https://doi.org/10.21437/interspeech.2020-1963","mag":"3080993257"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1963","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1963","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.10984","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023415990","display_name":"Martin Radfar","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":"Martin Radfar","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"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/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":"Athanasios Mouchtaris","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074068808","display_name":"Siegfried Kunzmann","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":"Siegfried Kunzmann","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210089985"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"866","last_page":"870"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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/T10028","display_name":"Topic Modeling","score":0.9962999820709229,"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":0.8187733292579651},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7190708518028259},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5872814655303955},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5452223420143127},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5165364146232605},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4957347810268402},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.49195143580436707},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48807084560394287},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4749222695827484},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4641614556312561},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.45832809805870056},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.451946496963501},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4469911456108093},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35981085896492004}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8187733292579651},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7190708518028259},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5872814655303955},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5452223420143127},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5165364146232605},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4957347810268402},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.49195143580436707},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48807084560394287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4749222695827484},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4641614556312561},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.45832809805870056},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.451946496963501},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4469911456108093},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35981085896492004},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-1963","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1963","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:2008.10984","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.10984","pdf_url":"https://arxiv.org/pdf/2008.10984","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":"text"},{"id":"mag:3080993257","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2008.10984.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.2008.10984","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.10984","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.10984","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.10984","pdf_url":"https://arxiv.org/pdf/2008.10984","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":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3080993257.pdf"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1984076147","https://openalex.org/W2024632416","https://openalex.org/W2091671846","https://openalex.org/W2130942839","https://openalex.org/W2137871902","https://openalex.org/W2153962611","https://openalex.org/W2194775991","https://openalex.org/W2327501763","https://openalex.org/W2397579082","https://openalex.org/W2399456070","https://openalex.org/W2599118679","https://openalex.org/W2891229414","https://openalex.org/W2892009249","https://openalex.org/W2894164357","https://openalex.org/W2928075308","https://openalex.org/W2963288440","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963418779","https://openalex.org/W2964052309","https://openalex.org/W2964108264","https://openalex.org/W2964308564","https://openalex.org/W3005910077","https://openalex.org/W3005915390","https://openalex.org/W3006901707","https://openalex.org/W3015412890","https://openalex.org/W3099944122","https://openalex.org/W3104113994"],"related_works":["https://openalex.org/W3095552229","https://openalex.org/W2977050317","https://openalex.org/W3138431698","https://openalex.org/W3133439430","https://openalex.org/W3132012095","https://openalex.org/W3197697656","https://openalex.org/W3015867372","https://openalex.org/W3092630929","https://openalex.org/W2513629222","https://openalex.org/W2073599923","https://openalex.org/W3209239055","https://openalex.org/W2899954925","https://openalex.org/W2884584040","https://openalex.org/W3151248472","https://openalex.org/W2166293310","https://openalex.org/W3155162503","https://openalex.org/W2928075308","https://openalex.org/W2808971413","https://openalex.org/W3095189764","https://openalex.org/W2891616026"],"abstract_inverted_index":{"Spoken":[0],"language":[1,34,46],"understanding":[2,47],"(SLU)":[3,48],"refers":[4],"to":[5,99,103,131,174],"the":[6,10,17,22,26,67,89,94,105,117,123,142,159,179,182],"process":[7],"of":[8,32,149,161,169],"inferring":[9],"semantic":[11,106],"information":[12],"from":[13],"audio":[14,77,95],"signals.":[15],"While":[16],"neural":[18,28,60,153],"transformers":[19],"consistently":[20],"deliver":[21],"best":[23],"performance":[24],"among":[25],"state-of-the-art":[27],"architectures":[29],"in":[30,39,75,122,178],"field":[31],"natural":[33],"processing":[35],"(NLP),":[36],"their":[37],"merits":[38],"a":[40,147,190],"closely":[41],"related":[42],"field,":[43],"i.e.,":[44],"spoken":[45],"have":[49],"not":[50],"beed":[51],"investigated.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56],"introduce":[57],"an":[58,76,110],"end-to-end":[59,113],"transformer-based":[61],"SLU":[62,115,143],"model":[63,163,183],"that":[64,145,168],"can":[65],"predict":[66],"variable-length":[68],"domain,":[69],"intent,":[70],"and":[71,120,136,140,151],"slots":[72,121],"vectors":[73],"embedded":[74],"signal":[78,96],"with":[79,128],"no":[80],"intermediate":[81],"token":[82],"prediction":[83],"architecture.":[84],"This":[85],"new":[86],"architecture":[87],"leverages":[88],"self-attention":[90,180],"mechanism":[91],"by":[92,109,155],"which":[93,187],"is":[97,164,184],"transformed":[98],"various":[100],"sub-subspaces":[101],"allowing":[102],"extract":[104],"context":[107],"implied":[108],"utterance.":[111],"Our":[112],"transformer":[114],"predicts":[116],"domains,":[118],"intents":[119],"Fluent":[124],"Speech":[125],"Commands":[126],"dataset":[127],"accuracy":[129],"equal":[130],"98.1":[132],"\\%,":[133,135,138],"99.6":[134,137],"respectively":[139],"outperforms":[141],"models":[144],"leverage":[146],"combination":[148],"recurrent":[150],"convolutional":[152],"networks":[154],"1.4":[156],"\\%":[157],"while":[158],"size":[160],"our":[162],"25\\%":[165],"smaller":[166],"than":[167],"these":[170],"architectures.":[171],"Additionally,":[172],"due":[173],"independent":[175],"sub-space":[176],"projections":[177],"layer,":[181],"highly":[185],"parallelizable":[186],"makes":[188],"it":[189],"good":[191],"candidate":[192],"for":[193],"on-device":[194],"SLU.":[195]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}