{"id":"https://openalex.org/W2928075308","doi":"https://doi.org/10.21437/interspeech.2019-2396","title":"Speech Model Pre-Training for End-to-End Spoken Language Understanding","display_name":"Speech Model Pre-Training for End-to-End Spoken Language Understanding","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2928075308","doi":"https://doi.org/10.21437/interspeech.2019-2396","mag":"2928075308"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2396","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/1904.03670","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040757409","display_name":"Loren Lugosch","orcid":"https://orcid.org/0000-0002-5024-8667"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Loren Lugosch","raw_affiliation_strings":["McGill University, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040811098","display_name":"Mirco Ravanelli","orcid":"https://orcid.org/0000-0002-3929-5526"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mirco Ravanelli","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al, Montreal, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000605765","display_name":"Patrick Ignoto","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick Ignoto","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083452139","display_name":"Vikrant Singh Tomar","orcid":"https://orcid.org/0009-0005-6509-9499"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Vikrant Singh Tomar","raw_affiliation_strings":["McGill University, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"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/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yoshua Bengio","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al, Montreal, Canada","institution_ids":["https://openalex.org/I70931966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5040757409"],"corresponding_institution_ids":["https://openalex.org/I5023651"],"apc_list":null,"apc_paid":null,"fwci":5.2022,"has_fulltext":true,"cited_by_count":41,"citation_normalized_percentile":{"value":0.96345454,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"814","last_page":"818"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.8510843515396118},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.8034178018569946},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5815678834915161},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5718702673912048},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5688357353210449},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.558245837688446},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.519827663898468},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5062486529350281},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5015597343444824},{"id":"https://openalex.org/keywords/gauge","display_name":"Gauge (firearms)","score":0.48230981826782227},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4286717474460602}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8510843515396118},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8034178018569946},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5815678834915161},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5718702673912048},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5688357353210449},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.558245837688446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.519827663898468},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5062486529350281},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5015597343444824},{"id":"https://openalex.org/C40976572","wikidata":"https://www.wikidata.org/wiki/Q2330873","display_name":"Gauge (firearms)","level":2,"score":0.48230981826782227},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4286717474460602},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2019-2396","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1904.03670","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.03670","pdf_url":"https://arxiv.org/pdf/1904.03670","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"mag:2928075308","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1904.03670","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.1904.03670","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1904.03670","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"},{"id":"doi:10.57702/symdo7l1","is_oa":true,"landing_page_url":"https://doi.org/10.57702/symdo7l1","pdf_url":null,"source":{"id":"https://openalex.org/S7407053387","display_name":"TIB Data Manager","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.03670","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.03670","pdf_url":"https://arxiv.org/pdf/1904.03670","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8399999737739563,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2165548363","display_name":null,"funder_award_id":"Canada","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G5784215521","display_name":null,"funder_award_id":"Chair","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G8595721295","display_name":null,"funder_award_id":"NSERC","funder_id":"https://openalex.org/F4320320994","funder_display_name":"Canada Research Chairs"},{"id":"https://openalex.org/G919846122","display_name":null,"funder_award_id":"Chair","funder_id":"https://openalex.org/F4320320994","funder_display_name":"Canada Research Chairs"}],"funders":[{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320314000","display_name":"Compute Canada","ror":"https://ror.org/03ty8yr27"},{"id":"https://openalex.org/F4320320994","display_name":"Canada Research Chairs","ror":"https://ror.org/0517h6h17"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2928075308.pdf","grobid_xml":"https://content.openalex.org/works/W2928075308.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W648947103","https://openalex.org/W1494198834","https://openalex.org/W1526990717","https://openalex.org/W2102113734","https://openalex.org/W2112796928","https://openalex.org/W2137871902","https://openalex.org/W2147768505","https://openalex.org/W2149933564","https://openalex.org/W2153962611","https://openalex.org/W2163605009","https://openalex.org/W2170973209","https://openalex.org/W2171144711","https://openalex.org/W2193413348","https://openalex.org/W2545177271","https://openalex.org/W2597757402","https://openalex.org/W2622203030","https://openalex.org/W2747874407","https://openalex.org/W2786459654","https://openalex.org/W2786839803","https://openalex.org/W2797583228","https://openalex.org/W2803609229","https://openalex.org/W2884254529","https://openalex.org/W2884975363","https://openalex.org/W2891229414","https://openalex.org/W2898771141","https://openalex.org/W2901616798","https://openalex.org/W2913340405","https://openalex.org/W2914151612","https://openalex.org/W2949079242","https://openalex.org/W2950577311","https://openalex.org/W2962835968","https://openalex.org/W2963026768","https://openalex.org/W2963070863","https://openalex.org/W2963168538","https://openalex.org/W2963288440","https://openalex.org/W2963303951","https://openalex.org/W2963341956","https://openalex.org/W2963522845","https://openalex.org/W2963703618","https://openalex.org/W2964052309","https://openalex.org/W2964108264"],"related_works":["https://openalex.org/W2963341956","https://openalex.org/W2963288440","https://openalex.org/W2891229414","https://openalex.org/W2894164357","https://openalex.org/W1494198834","https://openalex.org/W2972584841","https://openalex.org/W3157594170","https://openalex.org/W2786839803","https://openalex.org/W2327501763","https://openalex.org/W3093452977","https://openalex.org/W2981267975","https://openalex.org/W3015412890","https://openalex.org/W2977050317","https://openalex.org/W3004225838","https://openalex.org/W3133439430","https://openalex.org/W2963403868","https://openalex.org/W2842511635","https://openalex.org/W1524333225","https://openalex.org/W3171586554","https://openalex.org/W3132012095"],"abstract_inverted_index":{"Whereas":[0],"conventional":[1],"spoken":[2],"language":[3],"understanding":[4],"(SLU)":[5],"systems":[6,18],"map":[7,19],"speech":[8,20],"to":[9,14,22,49,64,113,118,120],"text,":[10],"and":[11,67,84,100],"then":[12],"text":[13],"intent,":[15],"end-to-end":[16,34,55],"SLU":[17,56,79],"directly":[21],"intent":[23],"through":[24],"a":[25,37,47,77,103],"single":[26],"trainable":[27],"model.":[28],"Achieving":[29],"high":[30],"accuracy":[31],"with":[32],"these":[33],"models":[35],"without":[36],"large":[38],"amount":[39],"of":[40,54],"training":[41,99],"data":[42,52],"is":[43,61,96,106],"difficult.":[44],"We":[45,75,108],"propose":[46],"method":[48,88],"reduce":[50],"the":[51,59,93,115],"requirements":[53],"in":[57],"which":[58],"model":[60],"first":[62],"pre-trained":[63],"predict":[65],"words":[66],"phonemes,":[68],"thus":[69],"learning":[70],"good":[71],"features":[72],"for":[73,98],"SLU.":[74],"introduce":[76],"new":[78,121],"dataset,":[80],"Fluent":[81],"Speech":[82],"Commands,":[83],"show":[85],"that":[86],"our":[87],"improves":[89],"performance":[90],"both":[91],"when":[92,101],"full":[94],"dataset":[95],"used":[97],"only":[102],"small":[104],"subset":[105],"used.":[107],"also":[109],"describe":[110],"preliminary":[111],"experiments":[112],"gauge":[114],"model's":[116],"ability":[117],"generalize":[119],"phrases":[122],"not":[123],"heard":[124],"during":[125],"training.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":13}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2019-04-11T00:00:00"}