{"id":"https://openalex.org/W3210679021","doi":"https://doi.org/10.1109/mapr53640.2021.9585267","title":"FastTacotron: A Fast, Robust and Controllable Method for Speech Synthesis","display_name":"FastTacotron: A Fast, Robust and Controllable Method for Speech Synthesis","publication_year":2021,"publication_date":"2021-10-01","ids":{"openalex":"https://openalex.org/W3210679021","doi":"https://doi.org/10.1109/mapr53640.2021.9585267","mag":"3210679021"},"language":"en","primary_location":{"id":"doi:10.1109/mapr53640.2021.9585267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mapr53640.2021.9585267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Multimedia Analysis and Pattern Recognition (MAPR)","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/A5025948040","display_name":"Dinh Viet Sang","orcid":"https://orcid.org/0000-0002-9254-1327"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Dinh Viet Sang","raw_affiliation_strings":["Hanoi University of Science and Technology, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053608425","display_name":"Lam Xuan Thu","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Lam Xuan Thu","raw_affiliation_strings":["Hanoi University of Science and Technology, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I94518387"],"apc_list":null,"apc_paid":null,"fwci":0.8394,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.79313018,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"51","issue":null,"first_page":"1","last_page":"5"},"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":0.9955000281333923,"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/T10028","display_name":"Topic Modeling","score":0.9950000047683716,"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":0.7819697856903076},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.7198410034179688},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6468759775161743},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.645672082901001},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5866472721099854},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5571239590644836},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5091835856437683},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.47128480672836304},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.44500964879989624},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42197558283805847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4070166349411011},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11498633027076721}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7819697856903076},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7198410034179688},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6468759775161743},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.645672082901001},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5866472721099854},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5571239590644836},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5091835856437683},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.47128480672836304},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44500964879989624},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42197558283805847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4070166349411011},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11498633027076721},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mapr53640.2021.9585267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mapr53640.2021.9585267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Multimedia Analysis and Pattern Recognition (MAPR)","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":37,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1599623585","https://openalex.org/W1836465849","https://openalex.org/W1924770834","https://openalex.org/W2016589492","https://openalex.org/W2064675550","https://openalex.org/W2090755665","https://openalex.org/W2102003408","https://openalex.org/W2107831318","https://openalex.org/W2111284386","https://openalex.org/W2120847449","https://openalex.org/W2129142580","https://openalex.org/W2150658333","https://openalex.org/W2154920538","https://openalex.org/W2194775991","https://openalex.org/W2542835211","https://openalex.org/W2747874407","https://openalex.org/W2903739847","https://openalex.org/W2945613576","https://openalex.org/W2946200149","https://openalex.org/W2963609956","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2972951102","https://openalex.org/W3015282541","https://openalex.org/W3025793647","https://openalex.org/W3096442195","https://openalex.org/W4294149591","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6640212811","https://openalex.org/W6676245417","https://openalex.org/W6728610325","https://openalex.org/W6763832098","https://openalex.org/W6780493881","https://openalex.org/W6917585676"],"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/W2998781440"],"abstract_inverted_index":{"Recent":[0],"state-of-the-art":[1,135],"neural":[2],"text-to-speech":[3,53],"synthesis":[4],"models":[5,24,31,136],"have":[6,18,33],"significantly":[7],"improved":[8,52],"the":[9,15,62,79,86,96,124,147,162,167,193,216],"quality":[10,141],"of":[11,110,139,149,166,180,196],"synthesized":[12],"speech.":[13],"However,":[14],"previous":[16],"methods":[17],"remained":[19],"several":[20],"problems.":[21],"While":[22],"autoregressive":[23,69],"suffer":[25],"from":[26],"slow":[27],"inference":[28,80,143],"speed,":[29,144],"non-autoregressive":[30],"usually":[32],"a":[34,44,73,92],"complicated,":[35],"time":[36,214],"and":[37,115,142,152,158,164],"memory-consuming":[38],"training":[39],"pipeline.":[40],"This":[41],"paper":[42],"proposes":[43],"novel":[45],"model":[46,60,83,133,173,198],"called":[47],"FastTacotron,":[48],"which":[49,182,204],"is":[50,183],"an":[51],"method":[54],"based":[55],"on":[56],"ForwardTacotron.":[57],"The":[58,82],"proposed":[59],"uses":[61],"recurrent":[63],"Tacotron":[64,90],"architecture":[65],"but":[66],"replacing":[67],"its":[68],"attentive":[70],"part":[71],"with":[72,91,201,215],"single":[74],"forward":[75],"pass":[76],"to":[77,122,160,185,208],"accelerate":[78],"speed.":[81],"also":[84],"replaces":[85],"attention":[87],"mechanism":[88],"in":[89,98,137,154,177,223],"length":[93],"regulator":[94],"like":[95],"one":[97,213],"FastSpeech":[99],"for":[100],"parallel":[101],"mel-spectrogram":[102],"generation.":[103],"Moreover,":[104],"we":[105],"introduce":[106],"more":[107,116,127],"prosodic":[108],"information":[109],"speech":[111,140],"(e.g.,":[112],"pitch,":[113],"energy,":[114],"accurate":[117],"duration)":[118],"as":[119],"conditional":[120],"inputs":[121],"make":[123],"duration":[125],"predictor":[126],"accurate.":[128],"Experiments":[129],"show":[130],"that":[131],"our":[132,172,197],"matches":[134],"terms":[138],"nearly":[145],"eliminates":[146],"problem":[148],"word":[150],"skipping":[151],"repeating":[153],"particularly":[155],"hard":[156],"cases,":[157],"possible":[159,207],"control":[161],"speed":[163],"pitch":[165],"generated":[168],"utterance.":[169],"More":[170],"importantly,":[171],"can":[174,220],"converge":[175],"just":[176],"few":[178],"hours":[179],"training,":[181],"up":[184],"11.2x":[186],"times":[187],"faster":[188],"than":[189],"existing":[190],"methods.":[191],"Furthermore,":[192],"memory":[194],"requirement":[195],"grows":[199],"linearly":[200],"sequence":[202],"length,":[203],"makes":[205],"it":[206],"predict":[209],"complete":[210],"articles":[211],"at":[212],"model.":[217],"Audio":[218],"samples":[219],"be":[221],"found":[222],"https://bit.ly/3xguaCW.":[224]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}