{"id":"https://openalex.org/W2973212992","doi":"https://doi.org/10.21437/interspeech.2019-2325","title":"Forward-Backward Decoding for Regularizing End-to-End TTS","display_name":"Forward-Backward Decoding for Regularizing End-to-End TTS","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2973212992","doi":"https://doi.org/10.21437/interspeech.2019-2325","mag":"2973212992"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2325","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"conference-paper","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/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibin Zheng","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442261","display_name":"Xi Wang","orcid":"https://orcid.org/0000-0002-5218-2761"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xi Wang","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061724331","display_name":"Lei He","orcid":"https://orcid.org/0000-0003-3028-6305"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei He","raw_affiliation_strings":["Southeast University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103063104","display_name":"Shifeng Pan","orcid":"https://orcid.org/0000-0002-9338-7800"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shifeng Pan","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank K. Soong","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqi Wen","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1283","last_page":"1287"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9897000193595886,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9860000014305115,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.8008019924163818},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7513400316238403},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.707801878452301},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.692570686340332},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6249178647994995},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5430772304534912},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5091540217399597},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.4458261728286743},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4404723346233368},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3711916208267212},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3355181813240051},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14982548356056213}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.8008019924163818},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7513400316238403},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.707801878452301},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.692570686340332},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6249178647994995},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5430772304534912},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5091540217399597},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4458261728286743},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4404723346233368},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3711916208267212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3355181813240051},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14982548356056213},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-2325","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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/W4288365855","https://openalex.org/W2948317131","https://openalex.org/W2111961547"],"abstract_inverted_index":{"Neural":[0],"end-to-end":[1],"TTS":[2],"can":[3],"generate":[4],"very":[5],"high-quality":[6],"synthesized":[7],"speech,":[8],"and":[9,69,97,104,114,132,163,184],"even":[10],"close":[11,186],"to":[12,26,61,87,129,135,187],"human":[13,188],"recording":[14],"within":[15],"similar":[16],"domain":[17],"text.":[18],"However,":[19],"it":[20,25],"performs":[21],"unsatisfactory":[22],"when":[23],"scaling":[24],"challenging":[27,182],"test":[28],"sets.":[29],"One":[30],"concern":[31],"is":[32,76],"that":[33],"the":[34,45,89,108,116,150],"encoder-decoder":[35],"with":[36,44,174],"attention-based":[37],"network":[38],"adopts":[39],"autoregressive":[40],"generative":[41],"sequence":[42],"model":[43,84],"limitation":[46],"of":[47,172,178],"exposure":[48],"bias":[49],"To":[50],"address":[51],"this":[52],"issue,":[53],"we":[54,123],"propose":[55],"two":[56,92],"novel":[57],"methods,":[58],"which":[59],"learn":[60],"predict":[62],"future":[63,117],"by":[64,78],"improving":[65],"agreement":[66],"between":[67,91],"forward":[68,131],"backward":[70,133],"decoding":[71,134],"sequence.":[72],"The":[73],"first":[74],"one":[75,110,152],"achieved":[77],"introducing":[79],"divergence":[80],"regularization":[81],"terms":[82],"into":[83],"training":[85,127],"objective":[86],"reduce":[88],"mismatch":[90],"directional":[93],"models,":[94],"namely":[95],"L2R":[96],"R2L":[98],"(which":[99],"generates":[100],"targets":[101],"from":[102],"left-to-right":[103],"right-to-left,":[105],"respectively).":[106],"While":[107],"second":[109,151],"operates":[111],"on":[112,160,195],"decoder-level":[113],"exploits":[115],"information":[118],"during":[119],"decoding.":[120],"In":[121],"addition,":[122],"employ":[124],"a":[125,157,175,181],"joint":[126],"strategy":[128],"allow":[130],"improve":[136],"each":[137],"other":[138],"in":[139,180,193],"an":[140],"interactive":[141],"process.":[142],"Experimental":[143],"results":[144],"show":[145],"our":[146],"proposed":[147],"methods":[148],"especially":[149],"(bidirectional":[153],"decoder":[154],"regularization),":[155],"leads":[156],"significantly":[158],"improvement":[159],"both":[161],"robustness":[162],"overall":[164],"naturalness,":[165],"as":[166],"outperforming":[167],"baseline":[168],"(the":[169],"revised":[170],"version":[171],"Tacotron2)":[173],"MOS":[176],"gap":[177],"0.14":[179],"test,":[183],"achieving":[185],"quality":[189],"(4.42":[190],"vs.":[191],"4.49":[192],"MOS)":[194],"general":[196],"test.":[197]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}