{"id":"https://openalex.org/W2972359262","doi":"https://doi.org/10.21437/interspeech.2019-2441","title":"LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech","display_name":"LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972359262","doi":"https://doi.org/10.21437/interspeech.2019-2441","mag":"2972359262"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2441","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2441","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":"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/A5003420204","display_name":"Heiga Zen","orcid":"https://orcid.org/0000-0002-8959-5471"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heiga Zen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006173011","display_name":"Viet Chau Dang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Viet Dang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052989202","display_name":"Rob Clark","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rob Clark","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100619178","display_name":"Zhang Yu","orcid":"https://orcid.org/0000-0003-2012-226X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103273436","display_name":"Ron J. Weiss","orcid":"https://orcid.org/0000-0003-2010-4053"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ron J. Weiss","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102792436","display_name":"Jia Ye","orcid":"https://orcid.org/0000-0002-8000-4911"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye Jia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100715424","display_name":"Zhifeng Chen","orcid":"https://orcid.org/0000-0001-8631-2424"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhifeng Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5010253402","display_name":"Yonghui Wu","orcid":"https://orcid.org/0000-0002-6780-6135"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yonghui Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":27.7805,"has_fulltext":false,"cited_by_count":747,"citation_normalized_percentile":{"value":0.99724462,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1526","last_page":"1530"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9970999956130981,"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":0.9970999956130981,"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/T10860","display_name":"Speech and Audio Processing","score":0.9646000266075134,"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/T12031","display_name":"Speech and dialogue systems","score":0.9449999928474426,"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/naturalness","display_name":"Naturalness","score":0.8651820421218872},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6647751331329346},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.627872109413147},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5153550505638123},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4375693202018738},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36445480585098267},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35900062322616577}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8651820421218872},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6647751331329346},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.627872109413147},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5153550505638123},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4375693202018738},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36445480585098267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35900062322616577},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-2441","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2441","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1574170747","https://openalex.org/W1597121597","https://openalex.org/W2033256038","https://openalex.org/W2103085228","https://openalex.org/W2105961775","https://openalex.org/W2129142580","https://openalex.org/W2182214061","https://openalex.org/W2293634267","https://openalex.org/W2604184139","https://openalex.org/W2736900972","https://openalex.org/W2747681982","https://openalex.org/W2788357188","https://openalex.org/W2794490148","https://openalex.org/W2808706139","https://openalex.org/W2885800352","https://openalex.org/W2889028433","https://openalex.org/W2892140764","https://openalex.org/W2892620417","https://openalex.org/W2901997113","https://openalex.org/W2963827314","https://openalex.org/W2964243274","https://openalex.org/W3177989406","https://openalex.org/W4232345992","https://openalex.org/W4289383906","https://openalex.org/W4294619240","https://openalex.org/W4295731579","https://openalex.org/W4298174729","https://openalex.org/W4298240696","https://openalex.org/W4298580827"],"related_works":["https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W2108985546","https://openalex.org/W2433276473","https://openalex.org/W2077992636","https://openalex.org/W1537411440","https://openalex.org/W2535215250","https://openalex.org/W2049083033","https://openalex.org/W290673751","https://openalex.org/W2017702615"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,49],"new":[4,38],"speech":[5,35,69],"corpus":[6,39,46,63,93],"called":[7],"\"LibriTTS\"":[8],"designed":[9],"for":[10,30,59],"text-to-speech":[11,60],"use.It":[12],"is":[13],"derived":[14],"from":[15,75,90],"the":[16,23,44,79,91],"original":[17],"audio":[18],"and":[19,32,78],"text":[20],"materials":[21],"of":[22,43,51,65,68,106],"LibriSpeech":[24,45,55],"corpus,":[25],"which":[26,53],"has":[27],"been":[28],"used":[29],"training":[31],"evaluating":[33],"automatic":[34],"recognition":[36],"systems.The":[37],"inherits":[40],"desired":[41],"properties":[42],"while":[47],"addressing":[48],"number":[50],"issues":[52],"make":[54],"less":[56],"than":[57],"ideal":[58],"work.The":[61],"released":[62],"consists":[64],"585":[66],"hours":[67],"data":[70],"at":[71],"24kHz":[72],"sampling":[73],"rate":[74],"2,456":[76],"speakers":[77],"corresponding":[80],"texts.Experimental":[81],"results":[82],"show":[83],"that":[84],"neural":[85],"end-to-end":[86],"TTS":[87],"models":[88],"trained":[89],"LibriTTS":[92],"achieved":[94],"above":[95],"4.0":[96],"in":[97,101,103],"mean":[98],"opinion":[99],"scores":[100],"naturalness":[102],"five":[104],"out":[105],"six":[107],"evaluation":[108],"speakers.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":59},{"year":2025,"cited_by_count":171},{"year":2024,"cited_by_count":155},{"year":2023,"cited_by_count":108},{"year":2022,"cited_by_count":75},{"year":2021,"cited_by_count":96},{"year":2020,"cited_by_count":71},{"year":2019,"cited_by_count":12}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}