{"id":"https://openalex.org/W3152289748","doi":"https://doi.org/10.21437/interspeech.2021-1679","title":"On-the-Fly Aligned Data Augmentation for Sequence-to-Sequence ASR","display_name":"On-the-Fly Aligned Data Augmentation for Sequence-to-Sequence ASR","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3152289748","doi":"https://doi.org/10.21437/interspeech.2021-1679","mag":"3152289748"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1679","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/2104.01393","any_repository_has_fulltext":true},"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"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Tsz Kin Lam","raw_affiliation_strings":["Heidelberg University"],"affiliations":[{"raw_affiliation_string":"Heidelberg University","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021977589","display_name":"Mayumi Ohta","orcid":"https://orcid.org/0000-0001-5354-5571"},"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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mayumi Ohta","raw_affiliation_strings":["Heidelberg University"],"affiliations":[{"raw_affiliation_string":"Heidelberg University","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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Shigehiko Schamoni","raw_affiliation_strings":["Heidelberg University"],"affiliations":[{"raw_affiliation_string":"Heidelberg University","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/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Riezler","raw_affiliation_strings":["Heidelberg University"],"affiliations":[{"raw_affiliation_string":"Heidelberg University","institution_ids":["https://openalex.org/I223822909"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5041285596"],"corresponding_institution_ids":["https://openalex.org/I223822909"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04456911,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.7443303465843201},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6459395289421082},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6015475988388062},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5114149451255798},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4422624409198761},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4408930838108063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3768882751464844}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7443303465843201},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6459395289421082},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6015475988388062},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5114149451255798},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4422624409198761},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4408930838108063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3768882751464844},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-1679","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.01393","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.01393","pdf_url":"https://arxiv.org/pdf/2104.01393","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:3152289748","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2104.01393.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.2104.01393","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.01393","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-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.01393","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.01393","pdf_url":"https://arxiv.org/pdf/2104.01393","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":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1515242458","https://openalex.org/W1932968309","https://openalex.org/W1979651826","https://openalex.org/W1981606737","https://openalex.org/W2099621636","https://openalex.org/W2107223151","https://openalex.org/W2112796928","https://openalex.org/W2156163116","https://openalex.org/W2171421863","https://openalex.org/W2407080277","https://openalex.org/W2747874407","https://openalex.org/W2766219058","https://openalex.org/W2885724687","https://openalex.org/W2888519496","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2963216553","https://openalex.org/W2963250244","https://openalex.org/W2964012862","https://openalex.org/W2965373594","https://openalex.org/W2972818416","https://openalex.org/W2989631226","https://openalex.org/W2992308087","https://openalex.org/W3015449694","https://openalex.org/W3015522062","https://openalex.org/W3015889230","https://openalex.org/W3094710821","https://openalex.org/W3096615836","https://openalex.org/W3098341425","https://openalex.org/W3099617520","https://openalex.org/W3103005696","https://openalex.org/W3107298252","https://openalex.org/W3118578889"],"related_works":["https://openalex.org/W3196824004","https://openalex.org/W3200151955","https://openalex.org/W3130315320","https://openalex.org/W3160523328","https://openalex.org/W2148182949","https://openalex.org/W3016053077","https://openalex.org/W3201953150","https://openalex.org/W2949174760","https://openalex.org/W3147962056","https://openalex.org/W2981762175","https://openalex.org/W2397119088","https://openalex.org/W2973049979","https://openalex.org/W3094965760","https://openalex.org/W2996856320","https://openalex.org/W3015356564","https://openalex.org/W2936794852","https://openalex.org/W2790982786","https://openalex.org/W2161482971","https://openalex.org/W1563861755","https://openalex.org/W2395971734"],"abstract_inverted_index":{"We":[0],"propose":[1],"an":[2,38,53],"on-the-fly":[3],"data":[4,86],"augmentation":[5],"method":[6],"for":[7,28],"automatic":[8],"speech":[9,35,48],"recognition":[10],"(ASR)":[11],"that":[12,56,83,104,117],"uses":[13],"alignment":[14],"information":[15],"to":[16,41,91],"generate":[17,42],"effective":[18],"training":[19,45,62,70,102],"samples.":[20],"Our":[21,110],"method,":[22],"called":[23],"Aligned":[24],"Data":[25],"Augmentation":[26],"(ADA)":[27],"ASR,":[29],"replaces":[30],"transcribed":[31,73],"tokens":[32,74],"and":[33,64,126,130,142],"the":[34,61,69,84,92],"representations":[36,49],"in":[37,101,107,134],"aligned":[39],"manner":[40],"previously":[43],"unseen":[44],"pairs.":[46],"The":[47,72],"are":[50,75,88],"sampled":[51],"from":[52,60],"audio":[54],"dictionary":[55],"has":[57],"been":[58],"extracted":[59],"corpus":[63],"inject":[65],"speaker":[66],"variations":[67],"into":[68],"examples.":[71],"either":[76],"predicted":[77],"by":[78],"a":[79,113],"language":[80],"model":[81],"such":[82],"augmented":[85],"pairs":[87,103],"semantically":[89],"close":[90],"original":[93],"data,":[94],"or":[95],"randomly":[96],"sampled.":[97],"Both":[98],"strategies":[99],"result":[100],"improve":[105],"robustness":[106],"ASR":[108],"training.":[109],"experiments":[111],"on":[112,122,139],"Seq-to-Seq":[114],"architecture":[115],"show":[116],"ADA":[118],"can":[119],"be":[120],"applied":[121],"top":[123],"of":[124],"SpecAugment,":[125],"achieves":[127],"about":[128],"9-23%":[129],"4-15%":[131],"relative":[132],"improvements":[133],"WER":[135],"over":[136],"SpecAugment":[137],"alone":[138],"LibriSpeech":[140,143],"100h":[141],"960h":[144],"test":[145],"datasets,":[146],"respectively.":[147]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}