{"id":"https://openalex.org/W2969521066","doi":"https://doi.org/10.1109/taslp.2019.2935807","title":"Forward\u2013Backward Decoding Sequence for Regularizing End-to-End TTS","display_name":"Forward\u2013Backward Decoding Sequence for Regularizing End-to-End TTS","publication_year":2019,"publication_date":"2019-08-22","ids":{"openalex":"https://openalex.org/W2969521066","doi":"https://doi.org/10.1109/taslp.2019.2935807","mag":"2969521066"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2935807","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2935807","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5101398585","display_name":"Yibin Zheng","orcid":"https://orcid.org/0000-0001-9158-1813"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yibin Zheng","raw_affiliation_strings":["School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9158-1813","affiliations":[{"raw_affiliation_string":"School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9437-7188"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9437-7188","affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111856667","display_name":"Zhengqi Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqi Wen","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078525423","display_name":"Jiangyan Yi","orcid":"https://orcid.org/0000-0003-2422-4618"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangyan Yi","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2422-4618","affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101398585"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":4.0459,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.95140959,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"27","issue":"12","first_page":"2067","last_page":"2079"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9965999722480774,"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":0.9961000084877014,"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/decoding-methods","display_name":"Decoding methods","score":0.7942877411842346},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7405745387077332},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6809853315353394},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6322466731071472},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5852280259132385},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.46761998534202576},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.4674901068210602},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4517565965652466},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.44751548767089844},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4405609369277954},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4237977862358093},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.4214553236961365},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4176759719848633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3346136510372162},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16316303610801697}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7942877411842346},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7405745387077332},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6809853315353394},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6322466731071472},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5852280259132385},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.46761998534202576},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4674901068210602},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4517565965652466},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44751548767089844},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4405609369277954},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4237977862358093},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.4214553236961365},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4176759719848633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3346136510372162},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16316303610801697},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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},{"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:10.1109/taslp.2019.2935807","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2935807","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6000000238418579}],"awards":[{"id":"https://openalex.org/G3237451694","display_name":null,"funder_award_id":"61603390","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7264488544","display_name":null,"funder_award_id":"61771472","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7663932412","display_name":null,"funder_award_id":"61425017","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G953811167","display_name":null,"funder_award_id":"61773379","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W84898526","https://openalex.org/W648786980","https://openalex.org/W854541894","https://openalex.org/W1492383498","https://openalex.org/W1499332833","https://openalex.org/W1522301498","https://openalex.org/W1527535554","https://openalex.org/W1570629387","https://openalex.org/W1576227399","https://openalex.org/W1584787447","https://openalex.org/W1599623585","https://openalex.org/W2055223207","https://openalex.org/W2102003408","https://openalex.org/W2104075463","https://openalex.org/W2120847449","https://openalex.org/W2124020686","https://openalex.org/W2129142580","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2154920538","https://openalex.org/W2406990556","https://openalex.org/W2423557781","https://openalex.org/W2466062786","https://openalex.org/W2519091744","https://openalex.org/W2619368999","https://openalex.org/W2752047430","https://openalex.org/W2766406951","https://openalex.org/W2794365787","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2808706139","https://openalex.org/W2885800352","https://openalex.org/W2889028433","https://openalex.org/W2889504751","https://openalex.org/W2892140764","https://openalex.org/W2963272440","https://openalex.org/W2963403868","https://openalex.org/W2963432880","https://openalex.org/W2963609956","https://openalex.org/W2963636093","https://openalex.org/W2963712897","https://openalex.org/W2963927338","https://openalex.org/W2964060510","https://openalex.org/W2964243274","https://openalex.org/W2964308564","https://openalex.org/W4295731579","https://openalex.org/W4385245566","https://openalex.org/W6621543089","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6635953567","https://openalex.org/W6675380101","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6738277540","https://openalex.org/W6739901393","https://openalex.org/W6743726175","https://openalex.org/W6745232783","https://openalex.org/W6749740488","https://openalex.org/W6750489868","https://openalex.org/W6752888775","https://openalex.org/W6754925833"],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W172797710","https://openalex.org/W3165080709","https://openalex.org/W2945105049","https://openalex.org/W2626699140","https://openalex.org/W2909357361","https://openalex.org/W4387098302","https://openalex.org/W2053269318","https://openalex.org/W2546021431","https://openalex.org/W2581127593"],"abstract_inverted_index":{"Neural":[0],"end-to-end":[1],"TTS":[2],"such":[3],"as":[4,95,135,240],"Tacotron":[5],"like":[6],"network":[7,44],"can":[8],"generate":[9],"very":[10],"high-quality":[11],"synthesized":[12],"speech,":[13],"and":[14,87,123,140,194,216,237,249,265,269],"even":[15],"close":[16,166],"to":[17,31,104,108,164,167,180,191,197,230],"human":[18],"recording":[19],"for":[20,267],"similar":[21],"domain":[22],"text.":[23],"However,":[24],"it":[25,30],"performs":[26],"unsatisfactory":[27],"when":[28],"scaling":[29],"some":[32,182],"challenging":[33,247],"test":[34],"sets.":[35],"One":[36],"concern":[37],"is":[38,97,209],"that":[39,220],"the":[40,51,83,110,131,142,152,158,168,171,186,225],"encoder-decoder":[41],"with":[42,50,260],"attention-based":[43],"adopts":[45],"autoregressive":[46],"generative":[47],"sequence":[48,65],"model":[49,105],"limitation":[52],"of":[53,155,174,258,263],"\u201cexposure":[54],"bias\u201d:":[55],"errors":[56],"made":[57],"early":[58],"could":[59],"be":[60,165],"quickly":[61],"amplified,":[62],"harming":[63],"subsequent":[64],"generation.":[66],"To":[67],"address":[68],"this":[69],"issue,":[70],"we":[71],"propose":[72],"two":[73,113],"novel":[74],"methods,":[75],"which":[76],"aim":[77],"at":[78],"predicting":[79],"future":[80,143],"by":[81,99],"improving":[82],"agreement":[84,111],"between":[85,112],"forward":[86,193],"backward":[88,195],"decoding":[89,196],"sequence.":[90],"The":[91],"first":[92],"one":[93,133,227],"(denoted":[94,134],"MRBA)":[96],"achieved":[98],"adding":[100],"divergence":[101],"regularization":[102,149],"terms":[103],"training":[106,153,207],"objective":[107,154],"maximize":[109],"directional":[114],"models,":[115],"namely":[116],"L2R":[117],"(which":[118,125],"generates":[119,126],"targets":[120,127],"from":[121,128],"left-to-right)":[122],"R2L":[124],"right-to-left).":[129],"While":[130],"second":[132,226],"BDR)":[136],"operates":[137],"on":[138,213,234,274],"decoder-level":[139],"exploits":[141],"information":[144,184],"during":[145],"decoding.":[146],"By":[147],"introducing":[148],"term":[150],"into":[151],"forward-backward":[156],"decoders,":[157],"forward-decoder's":[159],"hidden":[160,172],"states":[161],"are":[162,178],"forced":[163],"backward-decoder's.":[169],"Thus,":[170],"representations":[173],"a":[175,205,231,246,261,275],"unidirectional":[176],"decoder":[177],"encouraged":[179],"embed":[181],"useful":[183],"about":[185],"future.":[187],"Moreover,":[188],"in":[189,201,245,271],"order":[190],"make":[192],"improve":[198],"each":[199],"other":[200],"an":[202],"interactive":[203],"process,":[204],"joint":[206],"method":[208],"designed.":[210],"Experimental":[211],"results":[212],"both":[214,235],"English":[215,268],"Mandarin":[217,270],"dataset":[218],"show":[219],"our":[221],"proposed":[222],"methods":[223],"especially":[224],"(BDR),":[228],"lead":[229],"significantly":[232],"improvement":[233],"robustness":[236],"overall":[238],"naturalness,":[239],"achieving":[241,250],"obvious":[242],"preference":[243],"advantages":[244],"test,":[248],"state-of-the-art":[251],"performance":[252],"(outperforming":[253],"baseline":[254],"\u201cthe":[255],"revised":[256],"version":[257],"Tacotron2\u201d":[259],"gap":[262],"0.13":[264],"0.12":[266],"MOS,":[272],"respectively)":[273],"general":[276],"test.":[277]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}