{"id":"https://openalex.org/W2964281804","doi":null,"title":"Deep Voice: Real-time Neural Text-to-Speech","display_name":"Deep Voice: Real-time Neural Text-to-Speech","publication_year":2017,"publication_date":"2017-02-25","ids":{"openalex":"https://openalex.org/W2964281804","mag":"2964281804"},"language":"en","primary_location":{"id":"mag:2964281804","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/v70/arik17a/arik17a.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"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/A5037420650","display_name":"Sercan \u00d6. Ar\u0131k","orcid":"https://orcid.org/0000-0001-6333-1729","observed_orcids":["https://orcid.org/0000-0001-6333-1729"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sercan \u00d6. Ar\u0131k","raw_affiliation_strings":["Stanford University, Stanford, United States"],"raw_orcid":"https://orcid.org/0000-0001-6333-1729","affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, United States","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025020764","display_name":"Mike Chrzanowski","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mike Chrzanowski","raw_affiliation_strings":["Baidu (China), Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu (China), Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103153292","display_name":"Adam Coates","orcid":"https://orcid.org/0000-0002-4004-1603","observed_orcids":["https://orcid.org/0000-0002-4004-1603"]},"institutions":[{"id":"https://openalex.org/I11983389","display_name":"Manchester Metropolitan University","ror":"https://ror.org/02hstj355","country_code":"GB","type":"education","lineage":["https://openalex.org/I11983389"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Adam Coates","raw_affiliation_strings":["Manchester Metropolitan University, Manchester, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-4004-1603","affiliations":[{"raw_affiliation_string":"Manchester Metropolitan University, Manchester, United Kingdom","institution_ids":["https://openalex.org/I11983389"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006631932","display_name":"Gregory Diamos","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gregory Diamos","raw_affiliation_strings":["Baidu (China), Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu (China), Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011235394","display_name":"Andrew Gibiansky","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Andrew Gibiansky","raw_affiliation_strings":["Baidu (China), Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu (China), Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047212809","display_name":"Yongguo Kang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongguo Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066365471","display_name":"Xian Li","orcid":"https://orcid.org/0000-0003-0108-7665","observed_orcids":["https://orcid.org/0000-0003-0108-7665"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xian Li","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0108-7665","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028406576","display_name":"John J. Miller","orcid":"https://orcid.org/0000-0002-6390-9786","observed_orcids":["https://orcid.org/0000-0002-6390-9786"]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"J. J. Miller","raw_affiliation_strings":["Baidu (China), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6390-9786","affiliations":[{"raw_affiliation_string":"Baidu (China), Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102617494","display_name":"Andrew Y. Ng","orcid":"https://orcid.org/0000-0001-5547-3196","observed_orcids":["https://orcid.org/0000-0001-5547-3196"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Y. Ng","raw_affiliation_strings":["Stanford University, Stanford, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, United States","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058844317","display_name":"Jonathan Raiman","orcid":"https://orcid.org/0009-0000-5229-7318","observed_orcids":["https://orcid.org/0009-0000-5229-7318","https://orcid.org/0000-0002-7959-3229"]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jonathan Raiman","raw_affiliation_strings":["Baidu (China), Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-5229-7318","affiliations":[{"raw_affiliation_string":"Baidu (China), Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003509810","display_name":"Shubho Sengupta","orcid":"https://orcid.org/0009-0007-4204-5185","observed_orcids":["https://orcid.org/0009-0007-4204-5185"]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shubho Sengupta","raw_affiliation_strings":["Baidu (China), Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu (China), Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072436307","display_name":"Mohammad Shoeybi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mohammad Shoeybi","raw_affiliation_strings":["Baidu (China), Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu (China), Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.7173,"has_fulltext":false,"cited_by_count":93,"citation_normalized_percentile":{"value":0.97665892,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"195","last_page":"204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.0,"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/T11309","display_name":"Music and Audio Processing","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.8349999785423279},{"id":"https://openalex.org/keywords/end-to-end-speech-synthesis","display_name":"end-to-end speech synthesis","score":0.921999990940094},{"id":"https://openalex.org/keywords/real-time-speech-synthesis","display_name":"real-time speech synthesis","score":0.699999988079071},{"id":"https://openalex.org/keywords/phoneme-boundary-detection","display_name":"phoneme boundary detection","score":0.8349999785423279},{"id":"https://openalex.org/keywords/grapheme-to-phoneme-conversion","display_name":"grapheme-to-phoneme conversion","score":0.9660000205039978},{"id":"https://openalex.org/keywords/fundamental-frequency-prediction","display_name":"fundamental frequency prediction","score":0.9670000076293945},{"id":"https://openalex.org/keywords/wavenet","display_name":"WaveNet","score":0.8899999856948853},{"id":"https://openalex.org/keywords/connectionist-temporal-classification","display_name":"connectionist temporal classification","score":0.9589999914169312},{"id":"https://openalex.org/keywords/sound-synthesis","display_name":"sound synthesis","score":0.7960000038146973},{"id":"https://openalex.org/keywords/inference-acceleration","display_name":"inference acceleration","score":0.6150000095367432}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8433957099914551},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6884657144546509},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6682794690132141},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6473082900047302},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5812250971794128},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5741007328033447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5553283095359802},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5376824736595154},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47932589054107666},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.4571395516395569},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4570685625076294},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.43825405836105347},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4164081811904907},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.41181594133377075},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33546650409698486},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2964281804","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/v70/arik17a/arik17a.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2766812927","https://openalex.org/W2792995953","https://openalex.org/W3161789219","https://openalex.org/W2946200149","https://openalex.org/W2963712897","https://openalex.org/W3103702065","https://openalex.org/W1882624840","https://openalex.org/W2976348572","https://openalex.org/W2767052532","https://openalex.org/W3198213150"],"abstract_inverted_index":{"We":[0],"present":[1],"Deep":[2,13],"Voice,":[3],"a":[4,29,39,58,81],"production-quality":[5],"text-to-speech":[6,109],"system":[7,24,102,127],"constructed\nentirely":[8],"from":[9],"deep":[10,66],"neural":[11,20,67],"networks.":[12],"Voice":[14],"lays":[15],"the":[16,75,92],"groundwork":[17],"for":[18,32,98],"truly\nend-to-end":[19],"speech":[21],"synthesis.":[22],"The":[23],"comprises":[25],"five":[26],"major":[27],"building\nblocks:":[28],"segmentation":[30],"model":[31],"locating":[33],"phoneme":[34,40,63],"boundaries,":[35],"a\ngrapheme-to-phoneme":[36],"conversion":[37],"model,":[38,43,47,55,78],"duration":[41],"prediction":[42,46],"a\nfundamental":[44],"frequency":[45],"and":[48,88,105,117,135,143],"an":[49],"audio":[50,76],"synthesis":[51,77],"model.":[52],"For":[53,74],"the\nsegmentation":[54],"we":[56,79,122],"propose":[57],"novel":[59],"way":[60],"of":[61,83],"performing":[62],"boundary\ndetection":[64],"with":[65,125],"networks":[68],"using":[69,95],"connectionist":[70],"temporal":[71],"classification\n(CTC)":[72],"loss.":[73],"implement":[80],"variant":[82],"WaveNet\nthat":[84],"requires":[85,114],"fewer":[86],"parameters":[87],"trains":[89],"faster":[90,131],"than":[91,132],"original.":[93],"By":[94],"a\nneural":[96],"network":[97],"each":[99,112],"component,":[100],"our":[101,126],"is":[103],"simpler":[104],"more":[106],"flexible":[107],"than\ntraditional":[108],"systems,":[110],"where":[111],"component":[113],"laborious\nfeature":[115],"engineering":[116],"extensive":[118],"domain":[119],"expertise.":[120],"Finally,":[121],"show":[123],"that\ninference":[124],"can":[128],"be":[129],"performed":[130],"real":[133],"time":[134],"describe\noptimized":[136],"WaveNet":[137],"inference":[138],"kernels":[139],"on":[140],"both":[141],"CPU":[142],"GPU":[144],"that":[145],"achieve":[146],"up":[147],"to":[148],"400x\nspeedups":[149],"over":[150],"existing":[151],"implementations.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":27},{"year":2019,"cited_by_count":20},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-07-30T00:00:00"}