{"id":"https://openalex.org/W2989982989","doi":"https://doi.org/10.1109/sped.2019.8906584","title":"Towards End-to-End spoken intent recognition in smart home","display_name":"Towards End-to-End spoken intent recognition in smart home","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2989982989","doi":"https://doi.org/10.1109/sped.2019.8906584","mag":"2989982989"},"language":"en","primary_location":{"id":"doi:10.1109/sped.2019.8906584","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped.2019.8906584","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://biblio.ugent.be/publication/8750174","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020537654","display_name":"Thierry Desot","orcid":null},"institutions":[{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thierry Desot","raw_affiliation_strings":["GETALP Team, Univ. Grenoble Alpes, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GETALP Team, Univ. Grenoble Alpes, France","institution_ids":["https://openalex.org/I899635006"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079066445","display_name":"Fran\u00e7ois Portet","orcid":"https://orcid.org/0000-0003-2542-0661"},"institutions":[{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Francois Portet","raw_affiliation_strings":["GETALP Team, Univ. Grenoble Alpes, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GETALP Team, Univ. Grenoble Alpes, France","institution_ids":["https://openalex.org/I899635006"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067237858","display_name":"Michel Vacher","orcid":"https://orcid.org/0000-0001-7770-9171"},"institutions":[{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Michel Vacher","raw_affiliation_strings":["GETALP Team, Univ. Grenoble Alpes, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GETALP Team, Univ. Grenoble Alpes, France","institution_ids":["https://openalex.org/I899635006"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5908,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88084575,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T12031","display_name":"Speech and dialogue systems","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":0.9968000054359436,"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":0.8157496452331543},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7250233888626099},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6860706210136414},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6683691143989563},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48203861713409424},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.4494674503803253},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.44933459162712097},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.4315011501312256},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.42645734548568726},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4256252944469452},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.41893625259399414},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41875749826431274},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.41852259635925293},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.38920164108276367},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.337989866733551},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3358365297317505},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1163780689239502}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8157496452331543},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7250233888626099},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6860706210136414},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6683691143989563},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48203861713409424},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.4494674503803253},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.44933459162712097},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.4315011501312256},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.42645734548568726},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4256252944469452},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.41893625259399414},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41875749826431274},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.41852259635925293},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.38920164108276367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.337989866733551},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3358365297317505},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1163780689239502},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/sped.2019.8906584","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped.2019.8906584","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:8750174","is_oa":true,"landing_page_url":"https://biblio.ugent.be/publication/8750174","pdf_url":null,"source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9781728109848","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:archive.ugent.be:8750174","is_oa":true,"landing_page_url":"https://biblio.ugent.be/publication/8750174","pdf_url":null,"source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9781728109848","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3872131408","display_name":"Robust voice command adapted to the user and to the context for AAL","funder_award_id":"ANR-16-CE33-0006","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1500419248","https://openalex.org/W1524333225","https://openalex.org/W1738772085","https://openalex.org/W1762484328","https://openalex.org/W1922655562","https://openalex.org/W2009774589","https://openalex.org/W2010152689","https://openalex.org/W2134426579","https://openalex.org/W2135699042","https://openalex.org/W2137871902","https://openalex.org/W2193413348","https://openalex.org/W2250629451","https://openalex.org/W2251405085","https://openalex.org/W2327501763","https://openalex.org/W2397495166","https://openalex.org/W2415356462","https://openalex.org/W2604799547","https://openalex.org/W2618015847","https://openalex.org/W2736272491","https://openalex.org/W2759731798","https://openalex.org/W2890689696","https://openalex.org/W2898727538","https://openalex.org/W2899771611","https://openalex.org/W2914417638","https://openalex.org/W2949687426","https://openalex.org/W2954797783","https://openalex.org/W2962688168","https://openalex.org/W2962721878","https://openalex.org/W2962780374","https://openalex.org/W2963288440","https://openalex.org/W2963974889","https://openalex.org/W2980141581","https://openalex.org/W6631362777","https://openalex.org/W6637956674","https://openalex.org/W6640090968","https://openalex.org/W6679733325","https://openalex.org/W6687566353","https://openalex.org/W6691304110","https://openalex.org/W6712344656","https://openalex.org/W6715788442","https://openalex.org/W6744981885","https://openalex.org/W6752906821","https://openalex.org/W6756040250","https://openalex.org/W6756385397"],"related_works":["https://openalex.org/W2117488952","https://openalex.org/W134179020","https://openalex.org/W2184127972","https://openalex.org/W642007152","https://openalex.org/W2525874696","https://openalex.org/W2008120082","https://openalex.org/W2218471654","https://openalex.org/W4241475234","https://openalex.org/W1635592692","https://openalex.org/W3203521381"],"abstract_inverted_index":{"Voice":[0],"based":[1],"interaction":[2],"in":[3,72,152],"a":[4,9,26,73,146,153],"smart":[5,155],"home":[6,156],"has":[7],"become":[8],"feature":[10],"of":[11,47,125,148],"many":[12],"industrial":[13],"products.":[14],"These":[15],"systems":[16,39],"react":[17],"to":[18,43,98,167,182,189,197],"voice":[19,52,57,149],"commands,":[20],"whether":[21],"it":[22],"is":[23,58,111,164],"for":[24,114,136],"answering":[25],"question,":[27],"providing":[28],"music":[29],"or":[30],"turning":[31],"on":[32,145,200],"the":[33,45,48,51,70,76,80,86,104,126,133,159,168,183,195],"lights.":[34],"To":[35],"be":[36,41,130,187],"efficient,":[37],"these":[38],"must":[40],"able":[42],"extract":[44],"intent":[46,67,87,100,137],"user":[49],"from":[50,56,69,103],"command.":[53],"Intent":[54],"recognition":[55,64],"typically":[59],"performed":[60],"through":[61],"automatic":[62],"speech":[63,106,127],"(ASR)":[65],"and":[66,118],"classification":[68,101,138],"transcriptions":[71],"pipeline.":[74],"However,":[75,171],"errors":[77],"accumulated":[78],"at":[79],"ASR":[81],"stage":[82],"might":[83],"severely":[84],"impact":[85],"classifier.":[88],"In":[89],"this":[90,115],"paper,":[91],"we":[92,177],"propose":[93],"an":[94],"End-to-End":[95],"(E2E)":[96],"model":[97,135,185],"perform":[99],"directly":[102],"raw":[105],"input.":[107],"The":[108],"E2E":[109,134,169,184,201],"approach":[110],"thus":[112],"optimized":[113],"specific":[116],"task":[117],"avoids":[119],"error":[120],"propagation.":[121],"Furthermore,":[122],"prosodic":[123],"aspects":[124],"signal":[128],"can":[129,186],"exploited":[131],"by":[132],"(e.g.,":[139],"question":[140],"vs":[141],"imperative":[142],"voice).":[143],"Experiments":[144],"corpus":[147],"commands":[150],"acquired":[151],"real":[154],"reveal":[157],"that":[158,179],"state-of-the":[160],"art":[161],"pipeline":[162],"baseline":[163],"still":[165],"superior":[166],"approach.":[170],"using":[172],"artificial":[173],"data":[174],"generation":[175],"techniques":[176],"show":[178],"significant":[180],"improvement":[181],"brought":[188],"reach":[190],"competitive":[191],"performances.":[192],"This":[193],"opens":[194],"way":[196],"further":[198],"research":[199],"Spoken":[202],"Language":[203],"Understanding.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2026-06-20T22:02:38.213706","created_date":"2025-10-10T00:00:00"}