{"id":"https://openalex.org/W3153492756","doi":"https://doi.org/10.1109/icassp39728.2021.9413375","title":"Eat: Enhanced ASR-TTS for Self-Supervised Speech Recognition","display_name":"Eat: Enhanced ASR-TTS for Self-Supervised Speech Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3153492756","doi":"https://doi.org/10.1109/icassp39728.2021.9413375","mag":"3153492756"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413375","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.07474","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064113992","display_name":"Murali Karthick Baskar","orcid":"https://orcid.org/0000-0002-9396-6319"},"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":true,"raw_author_name":"Murali Karthick Baskar","raw_affiliation_strings":["Brno University of Technology","Brno University of Technology;"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology","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/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"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003156858","display_name":"Ram\u00f3n Fern\u00e1ndez Astudillo","orcid":"https://orcid.org/0000-0001-9443-2346"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramon Fernandez Astudillo","raw_affiliation_strings":["IBM Research"],"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"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":"Jan Honza Cernocky","raw_affiliation_strings":["Brno University of Technology"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5064113992"],"corresponding_institution_ids":["https://openalex.org/I60587646"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52907607,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"6753","last_page":"6757"},"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/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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9973000288009644,"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":0.677497148513794},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6491512656211853},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5940695405006409},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5893133878707886},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43654298782348633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3825189173221588},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3434862494468689},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15006408095359802}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.677497148513794},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6491512656211853},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5940695405006409},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5893133878707886},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43654298782348633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3825189173221588},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3434862494468689},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15006408095359802},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413375","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:2104.07474","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.07474","pdf_url":"https://arxiv.org/pdf/2104.07474","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3153492756","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2104.07474.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.2104.07474","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.07474","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/mtjm-xr58","is_oa":true,"landing_page_url":"https://doi.org/10.17023/mtjm-xr58","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.07474","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.07474","pdf_url":"https://arxiv.org/pdf/2104.07474","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320311687","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3153492756.pdf","grobid_xml":"https://content.openalex.org/works/W3153492756.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2119717200","https://openalex.org/W2586412610","https://openalex.org/W2883586237","https://openalex.org/W2890964092","https://openalex.org/W2898974134","https://openalex.org/W2903739847","https://openalex.org/W2936774411","https://openalex.org/W2943008652","https://openalex.org/W2951004968","https://openalex.org/W2962369866","https://openalex.org/W2962699523","https://openalex.org/W2963739817","https://openalex.org/W2964308564","https://openalex.org/W2972818416","https://openalex.org/W2972889948","https://openalex.org/W2988736778","https://openalex.org/W2991213871","https://openalex.org/W2998532468","https://openalex.org/W3015280134","https://openalex.org/W3015440759","https://openalex.org/W3015449694","https://openalex.org/W3015522062","https://openalex.org/W3015654635","https://openalex.org/W3015737168","https://openalex.org/W3016160783","https://openalex.org/W3036601975","https://openalex.org/W3099782249","https://openalex.org/W6640963894","https://openalex.org/W6679434410","https://openalex.org/W6753186555","https://openalex.org/W6755639519","https://openalex.org/W6765939562","https://openalex.org/W6770506093","https://openalex.org/W6770514103","https://openalex.org/W6772883055","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W3161143478","https://openalex.org/W2938947737","https://openalex.org/W3147900189","https://openalex.org/W3107204102","https://openalex.org/W3202690152","https://openalex.org/W3015853838","https://openalex.org/W2962699523","https://openalex.org/W3108006061","https://openalex.org/W3208480086","https://openalex.org/W1585767454","https://openalex.org/W3939953","https://openalex.org/W3153768731","https://openalex.org/W3197561413","https://openalex.org/W3131153302","https://openalex.org/W3208492395","https://openalex.org/W3015654635","https://openalex.org/W2028722051","https://openalex.org/W3007187541","https://openalex.org/W2296111744","https://openalex.org/W2401088934"],"abstract_inverted_index":{"Self-supervised":[0],"ASR-TTS":[1,13],"models":[2],"suffer":[3],"in":[4],"out-of-domain":[5,66,80],"data":[6,81],"conditions.":[7,82],"Here":[8],"we":[9],"propose":[10],"an":[11],"enhanced":[12],"(EAT)":[14],"model":[15,30,76],"that":[16,86],"incorporates":[17],"two":[18],"main":[19],"features:":[20],"1)":[21],"The":[22,83],"ASR\u2192TTS":[23],"direction":[24],"is":[25,49],"equipped":[26],"with":[27],"a":[28,47],"language":[29],"reward":[31],"to":[32,40,51,62,64],"penalize":[33],"the":[34,44,53,71,74,89],"ASR":[35,63],"hypotheses":[36],"before":[37,59],"forwarding":[38],"it":[39,61],"TTS.":[41],"2)":[42],"In":[43],"TTS\u2192ASR":[45],"direction,":[46],"hyper-parameter":[48],"introduced":[50],"scale":[52],"attention":[54],"context":[55],"from":[56],"synthesized":[57],"speech":[58],"sending":[60],"handle":[65],"data.":[67],"Training":[68],"strategies":[69],"and":[70,94,101,105],"effectiveness":[72],"of":[73],"EAT":[75,87],"are":[77],"explored":[78],"under":[79],"results":[84],"show":[85],"reduces":[88],"performance":[90],"gap":[91],"between":[92],"supervised":[93],"self-supervised":[95],"training":[96],"significantly":[97],"by":[98],"absolute":[99],"2.6%":[100],"2.7%":[102],"on":[103],"Librispeech":[104],"BABEL":[106],"respectively.":[107]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}