{"id":"https://openalex.org/W2938947737","doi":"https://doi.org/10.1109/icassp.2019.8682890","title":"Semi-supervised End-to-end Speech Recognition Using Text-to-speech and Autoencoders","display_name":"Semi-supervised End-to-end Speech Recognition Using Text-to-speech and Autoencoders","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2938947737","doi":"https://doi.org/10.1109/icassp.2019.8682890","mag":"2938947737"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682890","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682890","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5036532214","display_name":"Shigeki Karita","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shigeki Karita","raw_affiliation_strings":["NTT Communication Science Laboratories"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories","institution_ids":[]}]},{"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":["Center for Language and Speech Processing Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034538103","display_name":"Tomoharu Iwata","orcid":"https://orcid.org/0000-0003-4425-1971"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoharu Iwata","raw_affiliation_strings":["NTT Communication Science Laboratories"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Communication Science Laboratories"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101949937","display_name":"Atsunori Ogawa","orcid":"https://orcid.org/0000-0002-2888-101X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Atsunori Ogawa","raw_affiliation_strings":["NTT Communication Science Laboratories"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6166","last_page":"6170"},"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":0.9993000030517578,"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":0.9968000054359436,"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":0.8063267469406128},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7910813689231873},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6269654035568237},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6191908717155457},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6103398203849792},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48902758955955505},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.48394516110420227},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32436707615852356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8063267469406128},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7910813689231873},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6269654035568237},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6191908717155457},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6103398203849792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48902758955955505},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.48394516110420227},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32436707615852356},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682890","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682890","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.550000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1570629387","https://openalex.org/W1686810756","https://openalex.org/W2124558353","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2136922672","https://openalex.org/W2160815625","https://openalex.org/W2193413348","https://openalex.org/W2212660284","https://openalex.org/W2327501763","https://openalex.org/W2499126254","https://openalex.org/W2627092829","https://openalex.org/W2766812927","https://openalex.org/W2808706139","https://openalex.org/W2883586237","https://openalex.org/W2885724687","https://openalex.org/W2886180730","https://openalex.org/W2889213362","https://openalex.org/W2890964092","https://openalex.org/W2962699523","https://openalex.org/W2962780374","https://openalex.org/W2962826786","https://openalex.org/W2962835968","https://openalex.org/W2962947361","https://openalex.org/W2963432880","https://openalex.org/W2963602293","https://openalex.org/W2963609956","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964308564","https://openalex.org/W4298393544","https://openalex.org/W6629717138","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6676562027","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6687566353","https://openalex.org/W6688325169","https://openalex.org/W6702097088","https://openalex.org/W6734074887","https://openalex.org/W6736996214","https://openalex.org/W6745388339","https://openalex.org/W6745697700","https://openalex.org/W6752888775","https://openalex.org/W6753186555","https://openalex.org/W6754496211"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W2405439032","https://openalex.org/W2132658536","https://openalex.org/W2070212102","https://openalex.org/W2544241817","https://openalex.org/W2158882055","https://openalex.org/W2914603036","https://openalex.org/W2124470186"],"abstract_inverted_index":{"We":[0],"introduce":[1],"speech":[2,14,24,34,53,112],"and":[3,9,26,35,42,55,63,69,83,106,113,151],"text":[4,27,36,56],"autoencoders":[5,49],"that":[6,93],"share":[7],"encoders":[8,62],"decoders":[10,64],"with":[11,22,81,120,133,163],"an":[12],"automatic":[13],"recognition":[15],"(ASR)":[16],"model":[17,130,162],"to":[18,75,78,149,157],"improve":[19,99],"ASR":[20,41,68,82,101,105],"performance":[21,102],"large":[23,165],"only":[25,28,54,57],"training":[29,96,125],"datasets.":[30],"To":[31],"build":[32],"the":[33,61,67,100,139,143,161,169],"autoencoders,":[37],"we":[38,91,118],"leverage":[39],"state-of-the-art":[40],"text-to-speech":[43],"(TTS)":[44],"encoder":[45],"decoder":[46],"architectures.":[47],"These":[48],"learn":[50,109],"features":[51,77],"from":[52,128,147,155],"datasets":[58],"by":[59,86,159],"switching":[60],"used":[65],"in":[66,142],"TTS":[70,84,94,107],"models.":[71],"Simultaneously,":[72],"they":[73],"aim":[74],"encode":[76],"be":[79],"compatible":[80],"models":[85,108],"a":[87,129,134,164],"multi-task":[88],"loss.":[89],"Additionally,":[90],"anticipate":[92],"joint":[95],"can":[97],"also":[98],"because":[103],"both":[104],"transformations":[110],"between":[111],"text.":[114],"The":[115],"experimental":[116],"result":[117],"obtained":[119],"our":[121],"semi-supervised":[122],"end-to-end":[123],"ASR/TTS":[124],"revealed":[126],"reductions":[127],"initially":[131],"trained":[132],"small":[135],"paired":[136],"subset":[137,167],"of":[138,168],"LibriSpeech":[140],"corpus":[141],"character":[144],"error":[145,153],"rate":[146,154],"10.4%":[148],"8.4%":[150],"word":[152],"20.6%":[156],"18.0%":[158],"retraining":[160],"unpaired":[166],"corpus.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}