{"id":"https://openalex.org/W2964243274","doi":"https://doi.org/10.1109/icassp.2018.8461368","title":"Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions","display_name":"Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2964243274","doi":"https://doi.org/10.1109/icassp.2018.8461368","mag":"2964243274"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5021278619","display_name":"Jonathan Shen","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":true,"raw_author_name":"Jonathan Shen","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/A5112901893","display_name":"Ruoming Pang","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":"Ruoming Pang","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/A5103273436","display_name":"Ron J. Weiss","orcid":"https://orcid.org/0000-0003-2010-4053"},"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":"Ron J. Weiss","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/A5113452656","display_name":"Mike Schuster","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":"Mike Schuster","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/A5112445699","display_name":"Navdeep Jaitly","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":"Navdeep Jaitly","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/A5103011963","display_name":"Zongheng Yang","orcid":"https://orcid.org/0000-0001-8716-8743"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zongheng Yang","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100715424","display_name":"Zhifeng Chen","orcid":"https://orcid.org/0000-0001-8631-2424"},"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":"Zhifeng Chen","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/A5100707101","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-2842-6340"},"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":"middle","author":{"id":"https://openalex.org/A5101664515","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0009-0005-3508-3736"},"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/A5050900315","display_name":"Rj Skerrv-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":"Rj Skerrv-Ryan","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/A5026650852","display_name":"Rif A. Saurous","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":"Rif A. Saurous","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/A5058650235","display_name":"Yannis Agiomvrgiannakis","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":"Yannis Agiomvrgiannakis","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/A5010253402","display_name":"Yonghui Wu","orcid":"https://orcid.org/0000-0002-6780-6135"},"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":"Yonghui Wu","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":13,"corresponding_author_ids":["https://openalex.org/A5021278619"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":202.5697,"has_fulltext":false,"cited_by_count":2611,"citation_normalized_percentile":{"value":0.99989788,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4779","last_page":"4783"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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":0.995199978351593,"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/spectrogram","display_name":"Spectrogram","score":0.976399302482605},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6206014156341553},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6142116189002991},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.577618420124054},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.516390860080719},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5079458355903625},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48418429493904114},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46951526403427124},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4594669044017792},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4335479140281677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4114353060722351},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3839390277862549},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19361087679862976},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09885117411613464},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09244245290756226}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.976399302482605},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6206014156341553},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6142116189002991},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.577618420124054},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.516390860080719},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5079458355903625},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48418429493904114},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46951526403427124},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4594669044017792},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4335479140281677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4114353060722351},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3839390277862549},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19361087679862976},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09885117411613464},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09244245290756226},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1570629387","https://openalex.org/W1579853615","https://openalex.org/W1599623585","https://openalex.org/W1836465849","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2102003408","https://openalex.org/W2111284386","https://openalex.org/W2120847449","https://openalex.org/W2129142580","https://openalex.org/W2130942839","https://openalex.org/W2131774270","https://openalex.org/W2133564696","https://openalex.org/W2148154194","https://openalex.org/W2150658333","https://openalex.org/W2154920538","https://openalex.org/W2507771204","https://openalex.org/W2519091744","https://openalex.org/W2591927543","https://openalex.org/W2619368999","https://openalex.org/W2749651610","https://openalex.org/W2766812927","https://openalex.org/W2769810959","https://openalex.org/W2901997113","https://openalex.org/W2963609956","https://openalex.org/W2964301388","https://openalex.org/W4293714597","https://openalex.org/W4294619240","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6634817459","https://openalex.org/W6635953567","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6675380101","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6714142977","https://openalex.org/W6734815144","https://openalex.org/W6738277540","https://openalex.org/W6745697700","https://openalex.org/W6756197946"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2039489009"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"Tacotron":[3],"2,":[4],"a":[5,20,35,41,53,62,118],"neural":[6],"network":[7,25],"architecture":[8],"for":[9,66,117],"speech":[10],"synthesis":[11],"directly":[12],"from":[13,47],"text.":[14],"The":[15],"system":[16,84],"is":[17],"composed":[18],"of":[19,58,64,79,82,89,100,124],"recurrent":[21],"sequence-to-sequence":[22],"feature":[23],"prediction":[24],"that":[26,109],"maps":[27],"character":[28],"embeddings":[29],"to":[30,43,61,97],"mel-scale":[31],"spectrograms,":[32],"followed":[33],"by":[34],"modified":[36],"WaveNet":[37,98,126],"model":[38,51],"acting":[39],"as":[40,93],"vocoder":[42],"synthesize":[44],"time-domain":[45],"waveforms":[46],"those":[48],"spectrograms.":[49],"Our":[50],"achieves":[52],"mean":[54],"opinion":[55],"score":[56],"(MOS)":[57],"4.53":[59],"comparable":[60],"MOS":[63],"4.58":[65],"professionally":[67],"recorded":[68],"speech.":[69],"To":[70],"validate":[71],"our":[72,83],"design":[73],"choices,":[74],"we":[75],"present":[76],"ablation":[77],"studies":[78],"key":[80],"components":[81],"and":[85,103],"evaluate":[86],"the":[87,94,122,125],"impact":[88],"using":[90,110],"mel":[91],"spectrograms":[92],"conditioning":[95],"input":[96],"instead":[99],"linguistic,":[101],"duration,":[102],"F0":[104],"features.":[105],"We":[106],"further":[107],"show":[108],"this":[111],"compact":[112],"acoustic":[113],"intermediate":[114],"representation":[115],"allows":[116],"significant":[119],"reduction":[120],"in":[121],"size":[123],"architecture.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":89},{"year":2025,"cited_by_count":269},{"year":2024,"cited_by_count":281},{"year":2023,"cited_by_count":361},{"year":2022,"cited_by_count":413},{"year":2021,"cited_by_count":504},{"year":2020,"cited_by_count":387},{"year":2019,"cited_by_count":230},{"year":2018,"cited_by_count":74},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}