{"id":"https://openalex.org/W4372260590","doi":"https://doi.org/10.1109/icassp49357.2023.10094564","title":"Make More of Your Data: Minimal Effort Data Augmentation for Automatic Speech Recognition and Translation","display_name":"Make More of Your Data: Minimal Effort Data Augmentation for Automatic Speech Recognition and Translation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260590","doi":"https://doi.org/10.1109/icassp49357.2023.10094564"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094564","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041285596","display_name":"Tsz Kin Lam","orcid":null},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]},{"id":"https://openalex.org/I2802799214","display_name":"Association for Computational Linguistics","ror":"https://ror.org/019sw1443","country_code":"US","type":"other","lineage":["https://openalex.org/I2802799214"]}],"countries":["DE","US"],"is_corresponding":true,"raw_author_name":"Tsz Kin Lam","raw_affiliation_strings":["Heidelberg University,Computational Linguistics,Germany","Computational Linguistics, Heidelberg University, Germany"],"affiliations":[{"raw_affiliation_string":"Heidelberg University,Computational Linguistics,Germany","institution_ids":["https://openalex.org/I223822909","https://openalex.org/I2802799214"]},{"raw_affiliation_string":"Computational Linguistics, Heidelberg University, Germany","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068853519","display_name":"Shigehiko Schamoni","orcid":"https://orcid.org/0000-0002-0304-2412"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]},{"id":"https://openalex.org/I2802799214","display_name":"Association for Computational Linguistics","ror":"https://ror.org/019sw1443","country_code":"US","type":"other","lineage":["https://openalex.org/I2802799214"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Shigehiko Schamoni","raw_affiliation_strings":["Heidelberg University,Computational Linguistics,Germany","IWR, Heidelberg University, Germany","Computational Linguistics, Heidelberg University, Germany"],"affiliations":[{"raw_affiliation_string":"Heidelberg University,Computational Linguistics,Germany","institution_ids":["https://openalex.org/I223822909","https://openalex.org/I2802799214"]},{"raw_affiliation_string":"IWR, Heidelberg University, Germany","institution_ids":["https://openalex.org/I223822909"]},{"raw_affiliation_string":"Computational Linguistics, Heidelberg University, Germany","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011749347","display_name":"Stefan Riezler","orcid":null},"institutions":[{"id":"https://openalex.org/I2802799214","display_name":"Association for Computational Linguistics","ror":"https://ror.org/019sw1443","country_code":"US","type":"other","lineage":["https://openalex.org/I2802799214"]},{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Stefan Riezler","raw_affiliation_strings":["Heidelberg University,Computational Linguistics,Germany","IWR, Heidelberg University, Germany","Computational Linguistics, Heidelberg University, Germany"],"affiliations":[{"raw_affiliation_string":"Heidelberg University,Computational Linguistics,Germany","institution_ids":["https://openalex.org/I223822909","https://openalex.org/I2802799214"]},{"raw_affiliation_string":"IWR, Heidelberg University, Germany","institution_ids":["https://openalex.org/I223822909"]},{"raw_affiliation_string":"Computational Linguistics, Heidelberg University, Germany","institution_ids":["https://openalex.org/I223822909"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041285596"],"corresponding_institution_ids":["https://openalex.org/I223822909","https://openalex.org/I2802799214"],"apc_list":null,"apc_paid":null,"fwci":0.7842,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74373535,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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":0.9998000264167786,"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":0.9986000061035156,"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":0.8173410892486572},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.7945014238357544},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7192336320877075},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.5585263967514038},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5518279671669006},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.538698136806488},{"id":"https://openalex.org/keywords/carry","display_name":"Carry (investment)","score":0.4937537610530853},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43613603711128235},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39464491605758667},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.09005895256996155},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07478216290473938}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8173410892486572},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7945014238357544},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7192336320877075},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.5585263967514038},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5518279671669006},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.538698136806488},{"id":"https://openalex.org/C2776299755","wikidata":"https://www.wikidata.org/wiki/Q432449","display_name":"Carry (investment)","level":2,"score":0.4937537610530853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43613603711128235},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39464491605758667},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.09005895256996155},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07478216290473938},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094564","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6800000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2250342921","https://openalex.org/W2600463316","https://openalex.org/W2883586237","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2962699523","https://openalex.org/W2963250244","https://openalex.org/W2963362078","https://openalex.org/W2963532001","https://openalex.org/W2963739817","https://openalex.org/W3008480565","https://openalex.org/W3015280134","https://openalex.org/W3015889230","https://openalex.org/W3026041220","https://openalex.org/W3093579165","https://openalex.org/W3095350795","https://openalex.org/W3096338464","https://openalex.org/W3097777922","https://openalex.org/W3160525311","https://openalex.org/W3163839574","https://openalex.org/W3168212167","https://openalex.org/W3186321376","https://openalex.org/W3196824004","https://openalex.org/W3198840231","https://openalex.org/W4285215858","https://openalex.org/W4297841733","https://openalex.org/W6631190155","https://openalex.org/W6685320204","https://openalex.org/W6773238793","https://openalex.org/W6784050962","https://openalex.org/W6784614252","https://openalex.org/W6841035593"],"related_works":["https://openalex.org/W209733029","https://openalex.org/W2891480213","https://openalex.org/W2991483587","https://openalex.org/W3118953353","https://openalex.org/W2158542502","https://openalex.org/W1997978958","https://openalex.org/W133774893","https://openalex.org/W2099971677","https://openalex.org/W2250522181","https://openalex.org/W2615667245"],"abstract_inverted_index":{"Data":[0],"augmentation":[1],"is":[2,38],"a":[3],"technique":[4],"to":[5,27,40,75,92,96,141],"generate":[6],"new":[7,29],"training":[8,30,33,89,124],"data":[9,25,37,53],"based":[10],"on":[11,50,59,99,118,148],"existing":[12],"data.":[13,125],"We":[14,55,126],"evaluate":[15],"the":[16,23,51,60,100,113,119,122],"simple":[17],"and":[18,44,66,70,83,109,131],"cost-effective":[19],"method":[20,86,135],"of":[21,87,94,103,121],"concatenating":[22],"original":[24,52,123],"examples":[26],"build":[28],"instances.":[31],"Continued":[32],"with":[34,78],"such":[35],"augmented":[36],"able":[39],"improve":[41],"off-the-shelf":[42],"Transformer":[43],"Conformer":[45],"models":[46,76],"that":[47,112,133,151],"were":[48],"optimized":[49],"only.":[54],"demonstrate":[56,147],"considerable":[57],"improvements":[58,93],"LibriSpeech-960h":[61],"test":[62],"sets":[63],"(WER":[64,81],"2.83":[65],"6.87":[67],"for":[68,105,156],"test-clean":[69],"test-other),":[71],"which":[72],"carry":[73],"over":[74],"combined":[77],"shallow":[79],"fusion":[80],"2.55":[82],"6.27).":[84],"Our":[85],"continued":[88],"also":[90,154],"leads":[91],"up":[95],"0.9":[97],"WER":[98],"ASR":[101],"part":[102],"CoVoST-2":[104],"four":[106],"non-English":[107],"languages,":[108],"we":[110,146],"observe":[111],"gains":[114],"are":[115],"highly":[116],"dependent":[117],"size":[120],"compare":[127],"different":[128],"concatenation":[129],"strategies":[130],"found":[132],"our":[134,152],"does":[136],"not":[137],"need":[138],"speaker":[139],"information":[140],"achieve":[142],"its":[143],"improvements.":[144],"Finally,":[145],"two":[149],"datasets":[150],"methods":[153],"works":[155],"speech":[157],"translation":[158],"tasks.":[159]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}