{"id":"https://openalex.org/W3043902818","doi":"https://doi.org/10.3233/faia200605","title":"Data Augmentation for Pipeline-Based Speech Translation","display_name":"Data Augmentation for Pipeline-Based Speech Translation","publication_year":2020,"publication_date":"2020-09-15","ids":{"openalex":"https://openalex.org/W3043902818","doi":"https://doi.org/10.3233/faia200605","mag":"3043902818"},"language":"en","primary_location":{"id":"doi:10.3233/faia200605","doi":"https://doi.org/10.3233/faia200605","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia200605","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA200605","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"volume":null,"type":"book-chapter","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA200605","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018629040","display_name":"Diego Alves","orcid":"https://orcid.org/0000-0001-8311-2240","observed_orcids":["https://orcid.org/0000-0001-8311-2240"]},"institutions":[{"id":"https://openalex.org/I181343428","display_name":"University of Zagreb","ror":"https://ror.org/00mv6sv71","country_code":"HR","type":"education","lineage":["https://openalex.org/I181343428"]},{"id":"https://openalex.org/I4396570636","display_name":"Faculty of Humanities and Social Sciences in Zagreb","ror":"https://ror.org/03wtvtx73","country_code":"HR","type":"education","lineage":["https://openalex.org/I181343428","https://openalex.org/I4396570636"]}],"countries":["HR"],"is_corresponding":false,"raw_author_name":"Diego Alves","raw_affiliation_strings":["Faculty of Humanities and Social Sciences, University of Zagreb, Ul. Ivana Lu\u010di\u0107a 3, 10000, Zagreb, Croatia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Humanities and Social Sciences, University of Zagreb, Ul. Ivana Lu\u010di\u0107a 3, 10000, Zagreb, Croatia","institution_ids":["https://openalex.org/I181343428","https://openalex.org/I4396570636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045036749","display_name":"Askars Salimbajevs","orcid":"https://orcid.org/0000-0003-0165-0868","observed_orcids":["https://orcid.org/0000-0003-0165-0868"]},"institutions":[{"id":"https://openalex.org/I4210146923","display_name":"Tilde (Latvia)","ror":"https://ror.org/03jcesj83","country_code":"LV","type":"company","lineage":["https://openalex.org/I4210146923"]},{"id":"https://openalex.org/I91123046","display_name":"University of Latvia","ror":"https://ror.org/05g3mes96","country_code":"LV","type":"education","lineage":["https://openalex.org/I91123046"]}],"countries":["LV"],"is_corresponding":false,"raw_author_name":"Askars Salimbajevs","raw_affiliation_strings":["Tilde, Vien\u012bbas gatve 75A, Riga, Latvia, LV-1004","University of Latvia, Rai\u0146a bulv. 19-125, Riga, Latvia, LV-1586"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tilde, Vien\u012bbas gatve 75A, Riga, Latvia, LV-1004","institution_ids":["https://openalex.org/I4210146923"]},{"raw_affiliation_string":"University of Latvia, Rai\u0146a bulv. 19-125, Riga, Latvia, LV-1586","institution_ids":["https://openalex.org/I91123046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071261172","display_name":"M\u0101rcis Pinnis","orcid":"https://orcid.org/0000-0001-6832-5600","observed_orcids":["https://orcid.org/0000-0001-6832-5600"]},"institutions":[{"id":"https://openalex.org/I4210146923","display_name":"Tilde (Latvia)","ror":"https://ror.org/03jcesj83","country_code":"LV","type":"company","lineage":["https://openalex.org/I4210146923"]},{"id":"https://openalex.org/I91123046","display_name":"University of Latvia","ror":"https://ror.org/05g3mes96","country_code":"LV","type":"education","lineage":["https://openalex.org/I91123046"]}],"countries":["LV"],"is_corresponding":false,"raw_author_name":"M\u0101rcis Pinnis","raw_affiliation_strings":["Tilde, Vien\u012bbas gatve 75A, Riga, Latvia, LV-1004","University of Latvia, Rai\u0146a bulv. 19-125, Riga, Latvia, LV-1586"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tilde, Vien\u012bbas gatve 75A, Riga, Latvia, LV-1004","institution_ids":["https://openalex.org/I4210146923"]},{"raw_affiliation_string":"University of Latvia, Rai\u0146a bulv. 19-125, Riga, Latvia, LV-1586","institution_ids":["https://openalex.org/I91123046"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.951,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77849012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9189000129699707,"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":0.9189000129699707,"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":0.07530000060796738,"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":0.0017000000225380063,"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/data-augmentation","display_name":"data augmentation","score":0.7310000061988831},{"id":"https://openalex.org/keywords/speech-recognition-errors","display_name":"speech recognition errors","score":0.7400000095367432}],"concepts":[{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.8966631889343262},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.8335140943527222},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8300280570983887},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7386524677276611},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6769447326660156},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.630096971988678},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5317548513412476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5049181580543518},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.45154333114624023},{"id":"https://openalex.org/C2992676002","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Translation system","level":3,"score":0.43205684423446655},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41551387310028076},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09790158271789551},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09551870822906494},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C202751555","wikidata":"https://www.wikidata.org/wiki/Q221681","display_name":"In vitro","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/faia200605","doi":"https://doi.org/10.3233/faia200605","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia200605","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA200605","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:HAL:hal-02907053v1","doi":null,"is_oa":true,"landing_page_url":"https://inria.hal.science/hal-02907053","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"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":"9th International Conference on Human Language Technologies - the Baltic Perspective (Baltic HLT 2020), Sep 2020, Kaunas, Lithuania","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.3233/faia200605","doi":"https://doi.org/10.3233/faia200605","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia200605","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA200605","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3728728618","display_name":"Cross-lingual Event-centric Open Analytics Research Academy","funder_award_id":"812997","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G434337789","display_name":null,"funder_award_id":"HORIZON2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3043902818.pdf","grobid_xml":"https://content.openalex.org/works/W3043902818.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W46679369","https://openalex.org/W1647671624","https://openalex.org/W2124807415","https://openalex.org/W2150622104","https://openalex.org/W2466918907","https://openalex.org/W2593011301","https://openalex.org/W2746176496","https://openalex.org/W2795467683","https://openalex.org/W2805328873","https://openalex.org/W2902646476","https://openalex.org/W2948081755","https://openalex.org/W2962784628","https://openalex.org/W2963834942","https://openalex.org/W3020105517"],"related_works":["https://openalex.org/W6931060445","https://openalex.org/W6969297216","https://openalex.org/W4221161311","https://openalex.org/W4362706936","https://openalex.org/W4389518852","https://openalex.org/W4406859143","https://openalex.org/W7112839390","https://openalex.org/W2989819126","https://openalex.org/W4417285357","https://openalex.org/W2402827806"],"abstract_inverted_index":{"Pipeline-based":[0],"speech":[1,10,43,52,81],"translation":[2,20,44,82],"methods":[3,36,75],"may":[4],"suffer":[5],"from":[6],"errors":[7,57,66],"found":[8,64],"in":[9,76],"recognition":[11],"system":[12,45],"output.":[13],"Therefore,":[14],"it":[15],"is":[16],"crucial":[17],"that":[18,73],"machine":[19],"systems":[21],"are":[22],"trained":[23],"to":[24,55],"be":[25],"robust":[26],"against":[27],"such":[28],"noise.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33],"propose":[34],"two":[35],"for":[37,41],"parallel":[38],"data":[39],"augmentation":[40],"pipeline-based":[42],"development.":[46],"The":[47],"first":[48],"method":[49,61],"utilises":[50],"a":[51,68,89],"processing":[53],"workflow":[54],"introduce":[56],"and":[58],"the":[59,74],"second":[60],"generates":[62],"commonly":[63],"suffix":[65],"using":[67],"rule-based":[69],"method.":[70],"We":[71],"show":[72],"combination":[77],"allow":[78],"significantly":[79],"improving":[80],"quality":[83],"by":[84],"1.87":[85],"BLEU":[86],"points":[87],"over":[88],"baseline":[90],"system.":[91]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-07-29T00:00:00"}