{"id":"https://openalex.org/W2903739847","doi":"https://doi.org/10.1609/aaai.v33i01.33016706","title":"Neural Speech Synthesis with Transformer Network","display_name":"Neural Speech Synthesis with Transformer Network","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2903739847","doi":"https://doi.org/10.1609/aaai.v33i01.33016706","mag":"2903739847"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33016706","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33016706","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4642/4520","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4642/4520","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066219144","display_name":"Naihan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Naihan Li","raw_affiliation_strings":["University of Electronic Science and Techonoloy of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Techonoloy of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101635405","display_name":"Shujie Liu","orcid":"https://orcid.org/0009-0008-0785-8882"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shujie Liu","raw_affiliation_strings":["Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100360935","display_name":"Yanqing Liu","orcid":"https://orcid.org/0000-0003-0412-8805"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yanqing Liu","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329353","display_name":"Sheng Zhao","orcid":"https://orcid.org/0000-0002-9624-5381"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sheng Zhao","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100347765","display_name":"Ming Liu","orcid":"https://orcid.org/0000-0002-1114-1728"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Liu","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5066219144"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":56.5305,"has_fulltext":true,"cited_by_count":724,"citation_normalized_percentile":{"value":0.99966233,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"33","issue":"01","first_page":"6706","last_page":"6713"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9947999715805054,"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":0.9947999715805054,"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":0.9761999845504761,"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":0.9293000102043152,"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/computer-science","display_name":"Computer science","score":0.8025767207145691},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7912441492080688},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6168625950813293},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.605772852897644},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5923143029212952},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5846681594848633},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.568389356136322},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5488805770874023},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5377988815307617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4482918381690979},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.11812803149223328},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09938326478004456}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8025767207145691},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7912441492080688},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6168625950813293},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.605772852897644},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5923143029212952},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5846681594848633},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.568389356136322},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5488805770874023},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5377988815307617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4482918381690979},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.11812803149223328},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09938326478004456},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"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:10.1609/aaai.v33i01.33016706","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33016706","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4642/4520","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33016706","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33016706","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4642/4520","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2376276132","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2430228419","display_name":null,"funder_award_id":"ZYGX2016J084","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G251430071","display_name":null,"funder_award_id":"ZYGX2016J195","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2968268691","display_name":null,"funder_award_id":"2016J08","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G37568934","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4573120588","display_name":null,"funder_award_id":"ZYGX2015J155","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G4781244582","display_name":null,"funder_award_id":"GX2016","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6790179278","display_name":null,"funder_award_id":"61572113","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7033253288","display_name":null,"funder_award_id":"Grants","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7820223330","display_name":null,"funder_award_id":"6157211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8115478387","display_name":null,"funder_award_id":"61572113","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8951484681","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2903739847.pdf","grobid_xml":"https://content.openalex.org/works/W2903739847.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1599623585","https://openalex.org/W1991133427","https://openalex.org/W2102003408","https://openalex.org/W2111284386","https://openalex.org/W2120847449","https://openalex.org/W2129142580","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2148228080","https://openalex.org/W2150658333","https://openalex.org/W2154920538","https://openalex.org/W2157331557","https://openalex.org/W2168510624","https://openalex.org/W2519091744","https://openalex.org/W2584032004","https://openalex.org/W2587284713","https://openalex.org/W2604184139","https://openalex.org/W2613904329","https://openalex.org/W2766557690","https://openalex.org/W2804078698","https://openalex.org/W2901997113","https://openalex.org/W2962778134","https://openalex.org/W2963850025","https://openalex.org/W2963975282","https://openalex.org/W2964243274","https://openalex.org/W4294619240","https://openalex.org/W4298857617","https://openalex.org/W4301368689","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6666761814","https://openalex.org/W6676641785","https://openalex.org/W6679146927","https://openalex.org/W6679436768","https://openalex.org/W6756197946"],"related_works":["https://openalex.org/W3176018525","https://openalex.org/W3026554633","https://openalex.org/W2903810591","https://openalex.org/W2888520903","https://openalex.org/W2963499882","https://openalex.org/W3098873988","https://openalex.org/W2952599318","https://openalex.org/W2890256614","https://openalex.org/W2949454572","https://openalex.org/W2970247882"],"abstract_inverted_index":{"Although":[0],"end-to-end":[1],"neural":[2,37,48],"text-to-speech":[3],"(TTS)":[4],"methods":[5],"(such":[6],"as":[7,123],"Tacotron2)":[8],"are":[9,90,105,144],"proposed":[10,184],"and":[11,26,57,68,88,150,196],"achieve":[12],"state-of-theart":[13],"performance,":[14,177],"they":[15],"still":[16],"suffer":[17],"from":[18],"two":[19,100],"problems:":[20],"1)":[21],"low":[22],"efficiency":[23,149],"during":[24],"training":[25,96,167],"inference;":[27],"2)":[28],"hard":[29],"to":[30,63,137,146,200],"model":[31,185],"long":[32,115],"dependency":[33,117],"using":[34],"current":[35],"recurrent":[36],"networks":[38],"(RNNs).":[39],"Inspired":[40],"by":[41,108,133],"the":[42,59,65,70,77,82,86,114,139,148,157,166,176],"success":[43],"of":[44,79,152,194],"Transformer":[45,126,160],"network":[46,128,162],"in":[47,52,74,85,92,206],"machine":[49],"translation":[50],"(NMT),":[51],"this":[53],"paper,":[54],"we":[55],"introduce":[56],"adapt":[58],"multi-head":[60,80],"attention":[61,72],"mechanism":[62,73],"replace":[64],"RNN":[66],"structures":[67],"also":[69],"original":[71],"Tacotron2.":[75,174],"With":[76],"help":[78],"self-attention,":[81],"hidden":[83],"states":[84],"encoder":[87],"decoder":[89],"constructed":[91],"parallel,":[93],"which":[94,112],"improves":[95],"efficiency.":[97],"Meanwhile,":[98],"any":[99],"inputs":[101],"at":[102],"different":[103],"times":[104,170],"connected":[106],"directly":[107],"a":[109,134,192],"self-attention":[110],"mechanism,":[111],"solves":[113],"range":[116],"problem":[118],"effectively.":[119],"Using":[120],"phoneme":[121],"sequences":[122],"input,":[124],"our":[125,153,159,183],"TTS":[127,161],"generates":[129],"mel":[130],"spectrograms,":[131],"followed":[132],"WaveNet":[135],"vocoder":[136],"output":[138],"final":[140],"audio":[141],"results.":[142],"Experiments":[143],"conducted":[145],"test":[147],"performance":[151,188],"new":[154],"network.":[155],"For":[156,175],"efficiency,":[158],"can":[163],"speed":[164],"up":[165],"about":[168],"4.25":[169],"faster":[171],"compared":[172],"with":[173,191],"rigorous":[178],"human":[179,201],"tests":[180],"show":[181],"that":[182],"achieves":[186],"state-of-the-art":[187],"(outperforms":[189],"Tacotron2":[190],"gap":[193],"0.048)":[195],"is":[197],"very":[198],"close":[199],"quality":[202],"(4.39":[203],"vs":[204],"4.44":[205],"MOS).":[207]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":77},{"year":2024,"cited_by_count":91},{"year":2023,"cited_by_count":120},{"year":2022,"cited_by_count":126},{"year":2021,"cited_by_count":184},{"year":2020,"cited_by_count":100},{"year":2019,"cited_by_count":15}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}