{"id":"https://openalex.org/W2889028433","doi":"https://doi.org/10.1109/icassp.2019.8683862","title":"Semi-supervised Training for Improving Data Efficiency in End-to-end Speech Synthesis","display_name":"Semi-supervised Training for Improving Data Efficiency in End-to-end Speech Synthesis","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2889028433","doi":"https://doi.org/10.1109/icassp.2019.8683862","mag":"2889028433"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683862","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":"article","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/A5008107321","display_name":"Yu-An Chung","orcid":"https://orcid.org/0000-0001-9451-7956"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yu-An Chung","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103854502","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0000-0001-8269-3354"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051950818","display_name":"Wei-Ning Hsu","orcid":"https://orcid.org/0000-0001-5546-5217"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei-Ning Hsu","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433648","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-9505-1833"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066591543","display_name":"RJ Skerry-Ryan","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R.J. Skerry-Ryan","raw_affiliation_strings":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5008107321"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":10.9214,"has_fulltext":false,"cited_by_count":101,"citation_normalized_percentile":{"value":0.98636265,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6940","last_page":"6944"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T12031","display_name":"Speech and dialogue systems","score":0.9984999895095825,"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":0.7434747815132141},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7208216190338135},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6401640772819519},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5279048085212708},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49457666277885437},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4835050404071808},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36612993478775024}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7434747815132141},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7208216190338135},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6401640772819519},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5279048085212708},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49457666277885437},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4835050404071808},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36612993478775024},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683862","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1571950845","https://openalex.org/W1578102511","https://openalex.org/W1614298861","https://openalex.org/W1783473872","https://openalex.org/W1810943226","https://openalex.org/W2099062766","https://openalex.org/W2107860279","https://openalex.org/W2120847449","https://openalex.org/W2133564696","https://openalex.org/W2153579005","https://openalex.org/W2250539671","https://openalex.org/W2527729766","https://openalex.org/W2794490148","https://openalex.org/W2962739339","https://openalex.org/W2962970071","https://openalex.org/W2963272440","https://openalex.org/W2963609956","https://openalex.org/W2963975282","https://openalex.org/W2964243274","https://openalex.org/W2964308564","https://openalex.org/W2998704965","https://openalex.org/W4285719527","https://openalex.org/W4293714597","https://openalex.org/W4294170691","https://openalex.org/W6634201745","https://openalex.org/W6636510571","https://openalex.org/W6638081404","https://openalex.org/W6638273328","https://openalex.org/W6674610448","https://openalex.org/W6679434410","https://openalex.org/W6680532216","https://openalex.org/W6682691769","https://openalex.org/W6714142977","https://openalex.org/W6750489868","https://openalex.org/W6753855596","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W1999612375","https://openalex.org/W2997094352","https://openalex.org/W4394050964","https://openalex.org/W2551249631"],"abstract_inverted_index":{"Although":[0],"end-to-end":[1],"text-to-speech":[2],"(TTS)":[3],"models":[4],"such":[5],"as":[6],"Tacotron":[7,51,91,105,127],"have":[8],"shown":[9],"excellent":[10],"results,":[11],"they":[12],"typically":[13],"require":[14],"a":[15,35],"sizable":[16],"set":[17],"of":[18,44,138],"high-quality":[19],"<;text,":[20],"audio>":[21],"pairs":[22],"for":[23],"training,":[24],"which":[25],"are":[26,70],"expensive":[27],"to":[28,39,49,52,102,128],"collect.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33,77,112],"propose":[34],"semi-supervised":[36],"training":[37,140],"framework":[38,125],"improve":[40],"the":[41,82,90,104,108,114,123],"data":[42,69],"efficiency":[43],"Tacotron.":[45],"The":[46],"idea":[47],"is":[48],"allow":[50],"utilize":[53],"textual":[54],"and":[55,63,72,88],"acoustic":[56,109],"knowledge":[57],"contained":[58],"in":[59,81,107],"large,":[60],"publicly-available":[61],"text":[62,84],"speech":[64,100,131],"corpora.":[65],"Importantly,":[66],"these":[67],"external":[68],"unpaired":[71,99],"potentially":[73],"noisy.":[74],"Specifically,":[75],"first":[76],"embed":[78],"each":[79],"word":[80,86],"input":[83],"into":[85],"vectors":[87],"condition":[89],"encoder":[92],"on":[93],"them.":[94],"We":[95,120],"then":[96],"use":[97],"an":[98,136],"corpus":[101],"pre-train":[103],"decoder":[106],"domain.":[110],"Finally,":[111],"fine-tune":[113],"model":[115],"using":[116,132],"available":[117],"paired":[118,139],"data.":[119,141],"demonstrate":[121],"that":[122],"proposed":[124],"enables":[126],"generate":[129],"intelligible":[130],"less":[133],"than":[134],"half":[135],"hour":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}