{"id":"https://openalex.org/W2943008652","doi":"https://doi.org/10.21437/interspeech.2019-3167","title":"Semi-Supervised Sequence-to-Sequence ASR Using Unpaired Speech and Text","display_name":"Semi-Supervised Sequence-to-Sequence ASR Using Unpaired Speech and Text","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2943008652","doi":"https://doi.org/10.21437/interspeech.2019-3167","mag":"2943008652"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-3167","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-3167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/1905.01152","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;"],"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 Astudillo","raw_affiliation_strings":["IBM"],"affiliations":[{"raw_affiliation_string":"IBM","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087554069","display_name":"Takaaki Hori","orcid":"https://orcid.org/0000-0003-4560-8039"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takaaki Hori","raw_affiliation_strings":["MERL"],"affiliations":[{"raw_affiliation_string":"MERL","institution_ids":[]}]},{"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":"Luk\u00e1\u0161 Burget","raw_affiliation_strings":["Brno University of Technology;"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology;","institution_ids":["https://openalex.org/I60587646"]}]},{"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 \u010cernock\u00fd","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":6,"corresponding_author_ids":["https://openalex.org/A5064113992"],"corresponding_institution_ids":["https://openalex.org/I60587646"],"apc_list":null,"apc_paid":null,"fwci":1.1561,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84020077,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"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":0.9994999766349792,"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":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7905709147453308},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6502753496170044},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6112385392189026},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5571703314781189},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5004277229309082},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4391767382621765},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4183815121650696}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7905709147453308},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6502753496170044},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6112385392189026},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5571703314781189},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5004277229309082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4391767382621765},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4183815121650696},{"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":4,"locations":[{"id":"doi:10.21437/interspeech.2019-3167","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-3167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1905.01152","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.01152","pdf_url":"https://arxiv.org/pdf/1905.01152","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.1905.01152","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1905.01152","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:2943008652","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1905.01152","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.01152","pdf_url":"https://arxiv.org/pdf/1905.01152","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1503666391","display_name":null,"funder_award_id":"FA8650-17-C-9118","funder_id":"https://openalex.org/F4320338294","funder_display_name":"Air Force Research Laboratory"},{"id":"https://openalex.org/G3429874898","display_name":null,"funder_award_id":"LORELEI","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G656068760","display_name":null,"funder_award_id":"FA8650-17-C-9118","funder_id":"https://openalex.org/F4320333051","funder_display_name":"Intelligence Advanced Research Projects Activity"},{"id":"https://openalex.org/G8092615179","display_name":null,"funder_award_id":"HR0011-15-C-0115","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320312530","display_name":"Office of the Director of National Intelligence","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2943008652.pdf","grobid_xml":"https://content.openalex.org/works/W2943008652.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1494198834","https://openalex.org/W2024490156","https://openalex.org/W2064675550","https://openalex.org/W2102113734","https://openalex.org/W2130942839","https://openalex.org/W2131774270","https://openalex.org/W2133564696","https://openalex.org/W2193413348","https://openalex.org/W2327501763","https://openalex.org/W2546938941","https://openalex.org/W2627092829","https://openalex.org/W2750499125","https://openalex.org/W2883586237","https://openalex.org/W2890964092","https://openalex.org/W2892124901","https://openalex.org/W2898974134","https://openalex.org/W2913851961","https://openalex.org/W2949111211","https://openalex.org/W2962699523","https://openalex.org/W2962780374","https://openalex.org/W2962793481","https://openalex.org/W2962826786","https://openalex.org/W2963216553","https://openalex.org/W2963240019","https://openalex.org/W2963400424","https://openalex.org/W2963739817","https://openalex.org/W2964012862","https://openalex.org/W2964243274"],"related_works":["https://openalex.org/W2972889948","https://openalex.org/W2952711665","https://openalex.org/W3089863108","https://openalex.org/W2963739817","https://openalex.org/W2996353927","https://openalex.org/W3107298252","https://openalex.org/W3095304612","https://openalex.org/W2936774411","https://openalex.org/W1494198834","https://openalex.org/W3201101490","https://openalex.org/W2913851961","https://openalex.org/W2964999941","https://openalex.org/W2964161387","https://openalex.org/W2599118679","https://openalex.org/W3198047825","https://openalex.org/W3207222250","https://openalex.org/W2950548836","https://openalex.org/W3048379951","https://openalex.org/W3046609253","https://openalex.org/W3198460946"],"abstract_inverted_index":{"Sequence-to-sequence":[0],"automatic":[1],"speech":[2,62,99,124],"recognition":[3],"(ASR)":[4],"models":[5],"require":[6],"large":[7],"quantities":[8],"of":[9,111,120],"data":[10,65,102,121],"to":[11,59,95,103,143],"attain":[12],"high":[13],"performance.":[14],"For":[15],"this":[16,75],"reason,":[17],"there":[18],"has":[19],"been":[20],"a":[21,78],"recent":[22,38],"surge":[23],"in":[24,31,43,109,141],"interest":[25],"for":[26],"unsupervised":[27],"and":[28,48,56,100,123,125,128,134],"semi-supervised":[29,44,80],"training":[30,45,54],"such":[32],"models.":[33,72],"This":[34],"work":[35,76],"builds":[36],"upon":[37],"results":[39,116],"showing":[40],"notable":[41],"improvements":[42],"using":[46],"cycle-consistency":[47],"related":[49,107],"techniques.":[50],"Such":[51],"techniques":[52,108],"derive":[53],"procedures":[55],"losses":[57],"able":[58,94],"leverage":[60,96],"unpaired":[61,98],"and/or":[63],"text":[64,101,126],"by":[66],"combining":[67,82],"ASR":[68],"with":[69,88],"Text-to-Speech":[70],"(TTS)":[71],"In":[73],"particular,":[74],"proposes":[77],"new":[79],"loss":[81,87],"an":[83],"end-to-end":[84],"differentiable":[85],"ASR$\\rightarrow$TTS":[86],"TTS$\\rightarrow$ASR":[89],"loss.":[90],"The":[91],"method":[92],"is":[93,139],"both":[97],"outperform":[104],"recently":[105],"proposed":[106],"terms":[110],"\\%WER.":[112],"We":[113],"provide":[114],"extensive":[115],"analyzing":[117],"the":[118,145],"impact":[119],"quantity":[122],"modalities":[127],"show":[129],"consistent":[130],"gains":[131],"across":[132],"WSJ":[133],"Librispeech":[135],"corpora.":[136],"Our":[137],"code":[138],"provided":[140],"ESPnet":[142],"reproduce":[144],"experiments.":[146]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}