{"id":"https://openalex.org/W2912937645","doi":"https://doi.org/10.1109/slt.2018.8639589","title":"Leveraging Sequence-to-Sequence Speech Synthesis for Enhancing Acoustic-to-Word Speech Recognition","display_name":"Leveraging Sequence-to-Sequence Speech Synthesis for Enhancing Acoustic-to-Word Speech Recognition","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2912937645","doi":"https://doi.org/10.1109/slt.2018.8639589","mag":"2912937645"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","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/A5102851028","display_name":"Masato Mimura","orcid":"https://orcid.org/0000-0002-2403-0680"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Mimura","raw_affiliation_strings":["School of Informatics, Kyoto University, Sakyo-ku, Kyoto 606-8501, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Sakyo-ku, Kyoto 606-8501, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103835523","display_name":"Sei Ueno","orcid":"https://orcid.org/0000-0002-2255-3154"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sei Ueno","raw_affiliation_strings":["School of Informatics, Kyoto University, Sakyo-ku, Kyoto 606-8501, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Sakyo-ku, Kyoto 606-8501, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040282669","display_name":"Hirofumi Inaguma","orcid":"https://orcid.org/0000-0003-0610-1251"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirofumi Inaguma","raw_affiliation_strings":["School of Informatics, Kyoto University, Sakyo-ku, Kyoto 606-8501, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Sakyo-ku, Kyoto 606-8501, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110763152","display_name":"Shinsuke Sakai","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinsuke Sakai","raw_affiliation_strings":["School of Informatics, Kyoto University, Sakyo-ku, Kyoto 606-8501, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Sakyo-ku, Kyoto 606-8501, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["School of Informatics, Kyoto University, Sakyo-ku, Kyoto 606-8501, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Sakyo-ku, Kyoto 606-8501, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"477","last_page":"484"},"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/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9972000122070312,"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":0.8327111005783081},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7950923442840576},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6120995283126831},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5881630182266235},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.49826908111572266},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4902539551258087},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4736332297325134},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4557676911354065},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.448344886302948},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.44427254796028137},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.442740261554718},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4102059006690979},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3955965042114258},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39117950201034546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8327111005783081},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7950923442840576},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6120995283126831},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5881630182266235},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.49826908111572266},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4902539551258087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4736332297325134},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4557676911354065},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.448344886302948},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.44427254796028137},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.442740261554718},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4102059006690979},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3955965042114258},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39117950201034546},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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":1,"locations":[{"id":"doi:10.1109/slt.2018.8639589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1586532344","https://openalex.org/W1828163288","https://openalex.org/W1836465849","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2160815625","https://openalex.org/W2183341477","https://openalex.org/W2184045248","https://openalex.org/W2291513470","https://openalex.org/W2327501763","https://openalex.org/W2533523411","https://openalex.org/W2545177271","https://openalex.org/W2577366047","https://openalex.org/W2597757402","https://openalex.org/W2606833507","https://openalex.org/W2765486990","https://openalex.org/W2787663903","https://openalex.org/W2889074736","https://openalex.org/W2889504751","https://openalex.org/W2890197052","https://openalex.org/W2899771611","https://openalex.org/W2901997113","https://openalex.org/W2962699523","https://openalex.org/W2962826786","https://openalex.org/W2962961016","https://openalex.org/W2962970071","https://openalex.org/W2963240019","https://openalex.org/W2963266252","https://openalex.org/W2963483399","https://openalex.org/W2963609956","https://openalex.org/W2963691546","https://openalex.org/W2963920996","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W3034729383","https://openalex.org/W4293714597","https://openalex.org/W6621543089","https://openalex.org/W6623517193","https://openalex.org/W6629052376","https://openalex.org/W6631190155","https://openalex.org/W6635078382","https://openalex.org/W6638667902","https://openalex.org/W6638749077","https://openalex.org/W6674330103","https://openalex.org/W6675365184","https://openalex.org/W6714142977","https://openalex.org/W6728841359","https://openalex.org/W6735593169","https://openalex.org/W6741328424","https://openalex.org/W6745289305","https://openalex.org/W6746299031","https://openalex.org/W6748477376","https://openalex.org/W6749489859","https://openalex.org/W6756197946","https://openalex.org/W6779469704"],"related_works":["https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W2108985546","https://openalex.org/W2550171623","https://openalex.org/W2131711534","https://openalex.org/W1583620810","https://openalex.org/W2341426843","https://openalex.org/W1911859126","https://openalex.org/W642007152","https://openalex.org/W4387712795"],"abstract_inverted_index":{"Encoder-decoder":[0],"models":[1,25,50],"for":[2,11,87],"acoustic-to-word":[3],"(A2W)":[4],"automatic":[5],"speech":[6,48,79,107,112,116,121,125],"recognition":[7],"(ASR)":[8],"are":[9,127],"attractive":[10],"their":[12,41],"simplicity":[13],"of":[14,101,160],"architecture":[15],"and":[16,57],"run-time":[17],"latency":[18],"while":[19],"achieving":[20],"state-of-the-art":[21],"performances.":[22],"However,":[23],"word-based":[24],"commonly":[26],"suffer":[27],"from":[28,52,123,166],"the-of-vocabulary":[29],"(OOV)":[30],"word":[31,144],"problem.":[32],"They":[33],"also":[34],"cannot":[35],"leverage":[36,76],"text":[37,96],"data":[38,163],"to":[39,59,64,82,129,148],"improve":[40],"language":[42],"modeling":[43],"capability.":[44],"Recently,":[45],"sequence-to-sequence":[46,111],"neural":[47],"synthesis":[49,80],"trainable":[51],"corpora":[53,126],"have":[54],"been":[55],"developed":[56],"shown":[58],"achieve":[60],"naturalness":[61],"com-":[62],"parable":[63],"recorded":[65],"human":[66],"speech.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71,74,105],"explore":[72],"how":[73],"can":[75],"the":[77,84,139,143,149,154,161],"current":[78],"technology":[81],"tailor":[83],"ASR":[85],"system":[86],"a":[88,94,99,110,167],"target":[89,102],"domain":[90,103],"by":[91],"preparing":[92],"only":[93,152,165],"relevant":[95],"corpus.":[97],"From":[98],"set":[100],"texts,":[104],"generate":[106],"features":[108,117,122],"using":[109],"synthesizer.":[113],"These":[114],"artificial":[115],"together":[118],"with":[119,153],"real":[120,155],"conventional":[124],"used":[128],"train":[130],"an":[131],"attention-based":[132],"A2W":[133],"model.":[134],"Experimental":[135],"results":[136],"show":[137],"that":[138],"proposed":[140],"approach":[141],"improves":[142],"accuracy":[145],"significantly":[146],"compared":[147],"baseline":[150],"trained":[151],"speech,":[156],"although":[157],"synthetic":[158],"part":[159],"training":[162],"comes":[164],"single":[168],"female":[169],"speaker":[170],"voice.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}