{"id":"https://openalex.org/W2981267975","doi":"https://doi.org/10.1109/icassp40776.2020.9053063","title":"Using Speech Synthesis to Train End-To-End Spoken Language Understanding Models","display_name":"Using Speech Synthesis to Train End-To-End Spoken Language Understanding Models","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2981267975","doi":"https://doi.org/10.1109/icassp40776.2020.9053063","mag":"2981267975"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.09463.pdf","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"],"affiliations":[{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034701871","display_name":"Brett H. Meyer","orcid":"https://orcid.org/0000-0002-6650-3298"},"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":"Brett H. Meyer","raw_affiliation_strings":["McGill University"],"affiliations":[{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053824527","display_name":"Derek Nowrouzezahrai","orcid":"https://orcid.org/0000-0002-4279-1774"},"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":"Derek Nowrouzezahrai","raw_affiliation_strings":["McGill University"],"affiliations":[{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","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","Universit\u00e8 de Montreal"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I70931966"]},{"raw_affiliation_string":"Universit\u00e8 de Montreal","institution_ids":["https://openalex.org/I70931966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040757409"],"corresponding_institution_ids":["https://openalex.org/I5023651"],"apc_list":null,"apc_paid":null,"fwci":0.14685955,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50626275,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"8499","last_page":"8503"},"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/T10028","display_name":"Topic Modeling","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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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":0.8567637205123901},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7686768770217896},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7500902414321899},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7033807635307312},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5618006587028503},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5325186848640442},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5095313191413879},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4896393418312073},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4822255074977875},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4449571371078491},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4317414164543152},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.4240264892578125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8567637205123901},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7686768770217896},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7500902414321899},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7033807635307312},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5618006587028503},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5325186848640442},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5095313191413879},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4896393418312073},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4822255074977875},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4449571371078491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4317414164543152},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.4240264892578125},{"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/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"mag:2981267975","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.09463.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.1910.09463","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.09463","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:10.17023/7wrg-8e52","is_oa":true,"landing_page_url":"https://doi.org/10.17023/7wrg-8e52","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","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":"article"}],"best_oa_location":{"id":"mag:2981267975","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.09463.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},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1481659984","https://openalex.org/W1494198834","https://openalex.org/W1924770834","https://openalex.org/W2527729766","https://openalex.org/W2786839803","https://openalex.org/W2891229414","https://openalex.org/W2894164357","https://openalex.org/W2898727538","https://openalex.org/W2962760690","https://openalex.org/W2963288440","https://openalex.org/W2963403868","https://openalex.org/W2963534259","https://openalex.org/W2963708445","https://openalex.org/W2964308564","https://openalex.org/W2972314145","https://openalex.org/W2972327934","https://openalex.org/W2972584841","https://openalex.org/W2972880214","https://openalex.org/W2977838803","https://openalex.org/W3008480565","https://openalex.org/W3099944122","https://openalex.org/W3176896803","https://openalex.org/W6640212811","https://openalex.org/W6675365184","https://openalex.org/W6679434410","https://openalex.org/W6739901393","https://openalex.org/W6745569068","https://openalex.org/W6748263443","https://openalex.org/W6750074415","https://openalex.org/W6755077353","https://openalex.org/W6755871579","https://openalex.org/W6756385397","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W3015885816","https://openalex.org/W2928075308","https://openalex.org/W3133439430","https://openalex.org/W3093452977","https://openalex.org/W3004225838","https://openalex.org/W3029914199","https://openalex.org/W2977050317","https://openalex.org/W3148338017","https://openalex.org/W2172010760","https://openalex.org/W3098598562","https://openalex.org/W3091835551","https://openalex.org/W3016042119","https://openalex.org/W3015867372","https://openalex.org/W2073599923","https://openalex.org/W3171586554","https://openalex.org/W2786839803","https://openalex.org/W2913960647","https://openalex.org/W3016262400","https://openalex.org/W233551787","https://openalex.org/W2293858598"],"abstract_inverted_index":{"End-to-end":[0],"models":[1],"are":[2],"an":[3,17],"attractive":[4],"new":[5],"approach":[6],"to":[7,56,77],"spoken":[8],"language":[9,40],"understanding":[10,41],"(SLU)":[11],"in":[12,71],"which":[13,72],"the":[14,23,28,58,95],"meaning":[15],"of":[16,32,45,97,105,112],"utterance":[18],"is":[19,48,75],"inferred":[20],"directly":[21],"from":[22,84],"raw":[24],"audio":[25],"without":[26],"employing":[27],"standard":[29],"pipeline":[30],"composed":[31],"a":[33,65,79,102,110],"separately":[34],"trained":[35],"speech":[36,51,73],"recognizer":[37],"and":[38,108],"natural":[39],"module.":[42],"The":[43],"downside":[44],"end-to-end":[46],"SLU":[47,92],"that":[49],"in-domain":[50],"data":[52,107,113],"must":[53],"be":[54],"recorded":[55],"train":[57],"model.":[59],"In":[60],"this":[61,69],"paper,":[62],"we":[63],"propose":[64],"strategy":[66],"for":[67],"overcoming":[68],"requirement":[70],"synthesis":[74],"used":[76],"generate":[78],"large":[80],"synthetic":[81],"training":[82,106],"dataset":[83],"several":[85],"artificial":[86],"speakers.":[87],"Experiments":[88],"on":[89],"two":[90],"open-source":[91],"datasets":[93],"confirm":[94],"effectiveness":[96],"our":[98],"approach,":[99],"both":[100],"as":[101,109],"sole":[103],"source":[104],"form":[111],"augmentation.":[114]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}