{"id":"https://openalex.org/W3018778770","doi":"https://doi.org/10.1109/icassp39728.2021.9414159","title":"Jointly Trained Transformers Models for Spoken Language Translation","display_name":"Jointly Trained Transformers Models for Spoken Language Translation","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3018778770","doi":"https://doi.org/10.1109/icassp39728.2021.9414159","mag":"3018778770"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/2004.12111","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014351336","display_name":"Hari Krishna Vydana","orcid":"https://orcid.org/0000-0001-5192-5888"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Hari Krishna Vydana","raw_affiliation_strings":["Brno University of Technology, Faculty of Information Technology, Speech@FIT, Czechia","Brno University of Technology;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Faculty of Information Technology, Speech@FIT, Czechia","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Brno University of Technology;","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065253688","display_name":"Martin Karafi\u00e1t","orcid":"https://orcid.org/0000-0001-6474-8366"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Martin Karafiat","raw_affiliation_strings":["Brno University of Technology, Faculty of Information Technology, Speech@FIT, Czechia","Speech@FIT,Brno University of Technology, Faculty of Information Technology,Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Faculty of Information Technology, Speech@FIT, Czechia","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Speech@FIT,Brno University of Technology, Faculty of Information Technology,Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067790073","display_name":"Kate\u0159ina \u017dmol\u00edkov\u00e1","orcid":"https://orcid.org/0000-0003-4438-8580"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Katerina Zmolikova","raw_affiliation_strings":["Brno University of Technology, Faculty of Information Technology, Speech@FIT, Czechia","Speech@FIT,Brno University of Technology, Faculty of Information Technology,Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Faculty of Information Technology, Speech@FIT, Czechia","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Speech@FIT,Brno University of Technology, Faculty of Information Technology,Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lukas Burget","raw_affiliation_strings":["Brno University of Technology, Faculty of Information Technology, Speech@FIT, Czechia","Speech@FIT,Brno University of Technology, Faculty of Information Technology,Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Faculty of Information Technology, Speech@FIT, Czechia","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Speech@FIT,Brno University of Technology, Faculty of Information Technology,Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030520583","display_name":"Honza \u010cernock\u00fd","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Honza Cernocky","raw_affiliation_strings":["Brno University of Technology, Faculty of Information Technology, Speech@FIT, Czechia","Speech@FIT,Brno University of Technology, Faculty of Information Technology,Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Faculty of Information Technology, Speech@FIT, Czechia","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Speech@FIT,Brno University of Technology, Faculty of Information Technology,Czechia","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60587646"],"apc_list":null,"apc_paid":null,"fwci":0.5861,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.65723704,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"7513","last_page":"7517"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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/speech-translation","display_name":"Speech translation","score":0.8188124895095825},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8137721419334412},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6718133687973022},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6550890803337097},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6145668029785156},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5838594436645508},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.5591351389884949},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5349586606025696},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.46673309803009033},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43931296467781067},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4214757978916168},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3905346393585205},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08840858936309814},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07658180594444275}],"concepts":[{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.8188124895095825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8137721419334412},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6718133687973022},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6550890803337097},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6145668029785156},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5838594436645508},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.5591351389884949},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5349586606025696},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.46673309803009033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43931296467781067},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4214757978916168},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3905346393585205},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08840858936309814},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07658180594444275},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2004.12111","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.12111","pdf_url":"https://arxiv.org/pdf/2004.12111","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:3018778770","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2004.12111.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2004.12111","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2004.12111","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},{"id":"doi:10.17023/nbtc-a078","is_oa":true,"landing_page_url":"https://doi.org/10.17023/nbtc-a078","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":null,"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":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.12111","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.12111","pdf_url":"https://arxiv.org/pdf/2004.12111","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3018778770.pdf","grobid_xml":"https://content.openalex.org/works/W3018778770.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2892009249","https://openalex.org/W2892213699","https://openalex.org/W2936969148","https://openalex.org/W2943493972","https://openalex.org/W2963403868","https://openalex.org/W2963434219","https://openalex.org/W2972389417","https://openalex.org/W2972780808","https://openalex.org/W2972818416","https://openalex.org/W2973048981","https://openalex.org/W2978265966","https://openalex.org/W2995427493","https://openalex.org/W3015522062","https://openalex.org/W3016137827","https://openalex.org/W3042657922","https://openalex.org/W6730083651","https://openalex.org/W6739901393","https://openalex.org/W6755559483","https://openalex.org/W6761897164","https://openalex.org/W6769840780","https://openalex.org/W6775187155","https://openalex.org/W6775452034","https://openalex.org/W6776039324"],"related_works":["https://openalex.org/W3093981744","https://openalex.org/W2973107548","https://openalex.org/W2982129078","https://openalex.org/W3185037272","https://openalex.org/W1761757934","https://openalex.org/W3163239510","https://openalex.org/W3186883165","https://openalex.org/W3180526677","https://openalex.org/W3186272290","https://openalex.org/W2507334250","https://openalex.org/W2122511433","https://openalex.org/W3196833881","https://openalex.org/W2461468398","https://openalex.org/W90894508","https://openalex.org/W2400297987","https://openalex.org/W1971352820","https://openalex.org/W3186513069","https://openalex.org/W2161347348","https://openalex.org/W2950613790","https://openalex.org/W2488120195"],"abstract_inverted_index":{"End-to-End":[0,42,80],"and":[1,48,65,90,117,164,167],"cascade":[2],"(ASR-MT)":[3],"spoken":[4],"language":[5,165],"translation":[6,137,153],"(SLT)":[7],"systems":[8,57,119],"are":[9,69,132],"reaching":[10],"comparable":[11],"performances,":[12],"however,":[13],"a":[14],"large":[15],"degradation":[16,34],"is":[17,37,147],"observed":[18],"when":[19],"translating":[20],"the":[21,46,67,72,86,92,102,110,122,130,140,150],"ASR":[22,47,59,93,116],"hypothesis":[23],"in":[24,35],"comparison":[25],"to":[26,85,107,127],"using":[27,139,159,168],"oracle":[28],"input":[29],"text.":[30],"In":[31,51],"this":[32,52],"work,":[33,53],"performance":[36],"reduced":[38],"by":[39],"creating":[40],"an":[41,62,79],"differentiable":[43,81],"pipeline":[44],"between":[45],"MT":[49,118],"systems.":[50],"we":[54],"train":[55],"SLT":[56],"with":[58,83,113,149],"objective":[60,88,94],"as":[61],"auxiliary":[63],"loss":[64],"both":[66],"networks":[68],"connected":[70],"through":[71],"neural":[73],"hidden":[74],"representations.":[75],"This":[76,98],"training":[77,162],"has":[78,100],"path":[82],"respect":[84],"final":[87,144],"function":[89],"utilizes":[91],"for":[95],"better":[96],"optimization.":[97],"architecture":[99,112],"improved":[101,121],"BLEU":[103,123,145],"score":[104,124,146],"from":[105,125],"41.21":[106],"44.69.":[108],"Ensembling":[109],"proposed":[111],"independently":[114],"trained":[115],"further":[120],"44.69":[126],"46.9.":[128],"All":[129],"experiments":[131],"reported":[133],"on":[134,155],"English-Portuguese":[135],"speech":[136,152],"task":[138],"How2":[141,156],"corpus.":[142],"The":[143],"on-par":[148],"best":[151],"system":[154],"dataset":[157],"without":[158],"any":[160],"additional":[161],"data":[163],"model":[166],"fewer":[169],"parameters.":[170]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
