{"id":"https://openalex.org/W2982608933","doi":"https://doi.org/10.1109/icassp40776.2020.9054130","title":"Improving Sequence-To-Sequence Speech Recognition Training with On-The-Fly Data Augmentation","display_name":"Improving Sequence-To-Sequence Speech Recognition Training with On-The-Fly Data Augmentation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2982608933","doi":"https://doi.org/10.1109/icassp40776.2020.9054130","mag":"2982608933"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054130","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054130","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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.13296","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082064946","display_name":"Thai\u2010Son Nguyen","orcid":"https://orcid.org/0000-0001-7008-0462"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Thai-Son Nguyen","raw_affiliation_strings":["Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004861130","display_name":"Sebastian Stueker","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Stuker","raw_affiliation_strings":["Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046084081","display_name":"Jan Niehues","orcid":"https://orcid.org/0000-0002-4231-6543"},"institutions":[{"id":"https://openalex.org/I34352273","display_name":"Maastricht University","ror":"https://ror.org/02jz4aj89","country_code":"NL","type":"education","lineage":["https://openalex.org/I34352273"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jan Niehues","raw_affiliation_strings":["Department of Data Science and Knowledge Engineering (DKE), Maastricht University"],"affiliations":[{"raw_affiliation_string":"Department of Data Science and Knowledge Engineering (DKE), Maastricht University","institution_ids":["https://openalex.org/I34352273"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110453805","display_name":"Alex Waibel","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alex Waibel","raw_affiliation_strings":["Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082064946"],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":0.2718,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.62106987,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"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":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/T10201","display_name":"Speech Recognition and Synthesis","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983000159263611,"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/T11309","display_name":"Music and Audio Processing","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/overfitting","display_name":"Overfitting","score":0.9485895037651062},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7120224237442017},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6849849224090576},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5972209572792053},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5266563892364502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5113115310668945},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.47756487131118774},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4105275571346283},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37780943512916565},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35615819692611694},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1519775390625},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13652411103248596}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9485895037651062},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7120224237442017},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6849849224090576},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5972209572792053},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5266563892364502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5113115310668945},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.47756487131118774},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4105275571346283},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37780943512916565},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35615819692611694},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1519775390625},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13652411103248596},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054130","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054130","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":"pmh:oai:cris.maastrichtuniversity.nl:openaire_cris_publications/a3a1c015-ef89-4992-8bfc-9ac53f0e22ff","is_oa":false,"landing_page_url":"https://cris.maastrichtuniversity.nl/en/publications/a3a1c015-ef89-4992-8bfc-9ac53f0e22ff","pdf_url":null,"source":{"id":"https://openalex.org/S4306402616","display_name":"Research Publications (Maastricht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I34352273","host_organization_name":"Maastricht University","host_organization_lineage":["https://openalex.org/I34352273"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nguyen, T-S, St\u00fcker, S, Niehues, J & Waibel, A 2020, Improving Sequence-To-Sequence Speech Recognition Training with On-The-Fly Data Augmentation. in ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp. 7689-7693, 45th International Conference on Acoustics, Speech, and Signal Processing, Barcelona, Spain, 4/05/20. https://doi.org/10.1109/ICASSP40776.2020.9054130","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:1910.13296","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.13296","pdf_url":"https://arxiv.org/pdf/1910.13296","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":null,"raw_type":"text"},{"id":"mag:2982608933","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.13296.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.1910.13296","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.13296","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:10.17023/4t4f-8a37","is_oa":true,"landing_page_url":"https://doi.org/10.17023/4t4f-8a37","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"},{"id":"doi:10.5445/ir/1000128620","is_oa":true,"landing_page_url":"https://doi.org/10.5445/ir/1000128620","pdf_url":null,"source":{"id":"https://openalex.org/S7407052948","display_name":"KITopen","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-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.13296","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.13296","pdf_url":"https://arxiv.org/pdf/1910.13296","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":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2982608933.pdf","grobid_xml":"https://content.openalex.org/works/W2982608933.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1855892484","https://openalex.org/W1922655562","https://openalex.org/W1989674786","https://openalex.org/W2095705004","https://openalex.org/W2099621636","https://openalex.org/W2184343439","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2514741789","https://openalex.org/W2696967604","https://openalex.org/W2782451907","https://openalex.org/W2799800213","https://openalex.org/W2889163603","https://openalex.org/W2936774411","https://openalex.org/W2962824709","https://openalex.org/W2963070863","https://openalex.org/W2963266252","https://openalex.org/W2963403868","https://openalex.org/W2964121744","https://openalex.org/W2972451902","https://openalex.org/W2973040747","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6639156005","https://openalex.org/W6640090968","https://openalex.org/W6674330103","https://openalex.org/W6675409298","https://openalex.org/W6686369942","https://openalex.org/W6713762819","https://openalex.org/W6739901393","https://openalex.org/W6747836893"],"related_works":["https://openalex.org/W3168872064","https://openalex.org/W2766572290","https://openalex.org/W3165957370","https://openalex.org/W2922358226","https://openalex.org/W2793863914","https://openalex.org/W2737108017","https://openalex.org/W3118753411","https://openalex.org/W1495019370","https://openalex.org/W3097573669","https://openalex.org/W2572023240","https://openalex.org/W2776984718","https://openalex.org/W3155343771","https://openalex.org/W2900312178","https://openalex.org/W3144810982","https://openalex.org/W2953598317","https://openalex.org/W3182245104","https://openalex.org/W2775304348","https://openalex.org/W2972981541","https://openalex.org/W2886093827","https://openalex.org/W2891541684"],"abstract_inverted_index":{"Sequence-to-Sequence":[0],"(S2S)":[1],"models":[2,19,123],"recently":[3],"started":[4],"to":[5,37],"show":[6,118],"state-of-the-art":[7,119],"performance":[8,26,77,120],"for":[9,121],"automatic":[10],"speech":[11,130],"recognition":[12],"(ASR).":[13],"With":[14],"these":[15],"large":[16],"and":[17,49,108,115,133],"deep":[18],"overfitting":[20,39],"remains":[21],"the":[22,38,43,50,54,58,68,76,85,105,129],"largest":[23],"problem,":[24],"outweighing":[25],"improvements":[27],"that":[28,124],"can":[29],"be":[30],"obtained":[31],"from":[32,90],"better":[33],"architectures.":[34,82],"One":[35,83],"solution":[36],"problem":[40],"is":[41],"increasing":[42],"amount":[44],"of":[45,60,70,78,84],"available":[46],"training":[47,55,131],"data":[48,56,61,72,86,117,132],"variety":[51],"exhibited":[52],"by":[53],"with":[57],"help":[59],"augmentation.":[62],"In":[63],"this":[64],"paper":[65],"we":[66],"examine":[67],"influence":[69],"three":[71],"augmentation":[73,87],"methods":[74,95],"on":[75,113,128],"two":[79,93],"S2S":[80,122],"model":[81],"method":[88],"comes":[89],"literature,":[91],"while":[92],"other":[94],"are":[96,125],"our":[97],"own":[98],"development":[99],"-":[100],"a":[101],"time":[102],"perturbation":[103],"in":[104],"frequency":[106],"domain":[107],"sub-sequence":[109],"sampling.":[110],"Our":[111],"experiments":[112],"Switchboard":[114],"Fisher":[116],"trained":[126],"solely":[127],"do":[134],"not":[135],"use":[136],"additional":[137],"text":[138],"data.":[139]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}