{"id":"https://openalex.org/W4285215423","doi":"https://doi.org/10.1109/taslp.2022.3171974","title":"Decoding Knowledge Transfer for Neural Text-to-Speech Training","display_name":"Decoding Knowledge Transfer for Neural Text-to-Speech Training","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285215423","doi":"https://doi.org/10.1109/taslp.2022.3171974"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3171974","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3171974","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09767637.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09767637.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082746577","display_name":"Rui Liu","orcid":"https://orcid.org/0000-0003-4524-7413"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Liu","raw_affiliation_strings":["Department of Computer Science, Inner Mongolia University, Hohhot, China","computer science, Inner Mongolia University, 12576 Hohhot, Inner Mongolia, China, 010021"],"raw_orcid":"https://orcid.org/0000-0003-4524-7413","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"computer science, Inner Mongolia University, 12576 Hohhot, Inner Mongolia, China, 010021","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001303929","display_name":"Berrak \u015ei\u015fman","orcid":"https://orcid.org/0000-0001-8078-3305"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Berrak Sisman","raw_affiliation_strings":["Singapore University of Technology and Design (SUTD), Singapore","ISTD, Singapore University of Technology and Design, 233793 Singapore, Singapore, 138682"],"raw_orcid":"https://orcid.org/0000-0001-8078-3305","affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design (SUTD), Singapore","institution_ids":["https://openalex.org/I152815399"]},{"raw_affiliation_string":"ISTD, Singapore University of Technology and Design, 233793 Singapore, Singapore, 138682","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":["Department of Computer Science, Inner Mongolia University, Hohhot, China","College of Computer Science, Inner Mongolia University, Huhhot, Inner Mongolia, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Huhhot, Inner Mongolia, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","Department of Electrical and Computer Engineering, National University of Singapore, Singapore, Singapore, 117583"],"raw_orcid":"https://orcid.org/0000-0001-9158-9401","affiliations":[{"raw_affiliation_string":"School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore, Singapore, 117583","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5746,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.85489077,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"30","issue":null,"first_page":"1789","last_page":"1802"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9975000023841858,"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":0.7858747839927673},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6886569857597351},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6275674700737},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5699169635772705},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5574314594268799},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5565862059593201},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5489823818206787},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.5316007137298584},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5111663937568665},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"Knowledge transfer","score":0.4817047715187073},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.47483307123184204},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46511390805244446},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.4486232399940491},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09695422649383545}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7858747839927673},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6886569857597351},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6275674700737},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5699169635772705},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5574314594268799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5565862059593201},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5489823818206787},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.5316007137298584},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5111663937568665},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.4817047715187073},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.47483307123184204},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46511390805244446},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.4486232399940491},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09695422649383545},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","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/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/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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:10.1109/taslp.2022.3171974","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3171974","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09767637.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"id":"doi:10.1109/taslp.2022.3171974","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3171974","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09767637.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8399999737739563}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322216","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496"},{"id":"https://openalex.org/F4320324110","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285215423.pdf","grobid_xml":"https://content.openalex.org/works/W4285215423.grobid-xml"},"referenced_works_count":78,"referenced_works":["https://openalex.org/W1485981043","https://openalex.org/W1689711448","https://openalex.org/W2016589492","https://openalex.org/W2064675550","https://openalex.org/W2091653553","https://openalex.org/W2099471712","https://openalex.org/W2102003408","https://openalex.org/W2105482032","https://openalex.org/W2107860279","https://openalex.org/W2111284386","https://openalex.org/W2120847449","https://openalex.org/W2174424190","https://openalex.org/W2268617045","https://openalex.org/W2269051851","https://openalex.org/W2542835211","https://openalex.org/W2598638573","https://openalex.org/W2613330330","https://openalex.org/W2620998106","https://openalex.org/W2786868129","https://openalex.org/W2790783922","https://openalex.org/W2803525166","https://openalex.org/W2887585070","https://openalex.org/W2889026195","https://openalex.org/W2937408455","https://openalex.org/W2963084599","https://openalex.org/W2963321191","https://openalex.org/W2963609956","https://openalex.org/W2963736842","https://openalex.org/W2964243274","https://openalex.org/W2964345285","https://openalex.org/W2972448360","https://openalex.org/W2972702018","https://openalex.org/W2972746749","https://openalex.org/W2972789651","https://openalex.org/W2972817752","https://openalex.org/W2972951102","https://openalex.org/W2973212992","https://openalex.org/W2985308740","https://openalex.org/W2997006708","https://openalex.org/W2998115938","https://openalex.org/W3015338123","https://openalex.org/W3015499482","https://openalex.org/W3015735225","https://openalex.org/W3016151052","https://openalex.org/W3025182306","https://openalex.org/W3045672834","https://openalex.org/W3046667470","https://openalex.org/W3048768961","https://openalex.org/W3049756574","https://openalex.org/W3092822179","https://openalex.org/W3097540174","https://openalex.org/W3098557217","https://openalex.org/W3101313921","https://openalex.org/W3105136412","https://openalex.org/W3106690208","https://openalex.org/W3107061944","https://openalex.org/W3156778566","https://openalex.org/W3156828761","https://openalex.org/W3168542456","https://openalex.org/W3185635705","https://openalex.org/W4240592325","https://openalex.org/W4243859118","https://openalex.org/W4254751698","https://openalex.org/W6621543089","https://openalex.org/W6638523607","https://openalex.org/W6684191040","https://openalex.org/W6685322675","https://openalex.org/W6718379498","https://openalex.org/W6730161283","https://openalex.org/W6736588030","https://openalex.org/W6739901393","https://openalex.org/W6749489859","https://openalex.org/W6749555683","https://openalex.org/W6750489868","https://openalex.org/W6751751081","https://openalex.org/W6763832098","https://openalex.org/W6779871621","https://openalex.org/W6865583292"],"related_works":["https://openalex.org/W4308262314","https://openalex.org/W4382286161","https://openalex.org/W4386213806","https://openalex.org/W2960456850","https://openalex.org/W3021430260","https://openalex.org/W4281645081","https://openalex.org/W4312200629","https://openalex.org/W3084357355","https://openalex.org/W4317565044","https://openalex.org/W4362719745"],"abstract_inverted_index":{"Neural":[0],"end-to-end":[1],"text-to-speech":[2],"(TTS)":[3],"is":[4,73],"superior":[5],"to":[6,38,74,93,121],"conventional":[7],"statistical":[8],"methods":[9],"in":[10,29,41,81,157,182],"many":[11],"ways.":[12],"However,":[13],"the":[14,21,24,90,105,117,123,126,130,134,154,184],"exposure":[15,185],"bias":[16,186],"problem,":[17,50],"that":[18,97,104,149,173],"arises":[19],"from":[20],"mismatch":[22,135],"between":[23,136],"training":[25,137],"and":[26,59,84,88,138,145,162,166,179],"inference":[27],"process":[28],"autoregressive":[30],"models,":[31],"remains":[32],"an":[33,109],"issue.":[34],"It":[35],"often":[36],"leads":[37],"performance":[39],"degradation":[40],"face":[42],"of":[43,125,159],"out-of-domain":[44,167],"test":[45,168],"data.":[46,169],"To":[47],"address":[48],"this":[49],"we":[51,171],"study":[52],"a":[53,61,94],"novel":[54],"decoding":[55],"knowledge":[56,63,92,174],"transfer":[57,89],"strategy,":[58],"propose":[60],"multi-teacher":[62],"distillation":[64,175],"(MT-KD)":[65],"network":[66,107],"for":[67,112,164],"Tacotron2":[68,77],"TTS":[69,78,114],"model.":[70],"The":[71],"idea":[72],"pre-train":[75],"two":[76,127],"teacher":[79,82],"models":[80],"forcing":[83],"scheduled":[85],"sampling":[86],"modes,":[87],"pre-trained":[91],"student":[95,118],"model":[96,119],"performs":[98],"free":[99],"running":[100],"decoding.":[101],"We":[102],"show":[103,148,172],"MT-KD":[106,150],"provides":[108],"adequate":[110],"platform":[111],"neural":[113],"training,":[115],"where":[116],"learns":[120],"emulate":[122],"behaviors":[124],"teachers,":[128],"at":[129],"same":[131],"time,":[132],"minimizing":[133],"run-time":[139],"inference.":[140],"Experiments":[141],"on":[142],"both":[143],"Chinese":[144],"English":[146],"data":[147,180],"system":[151],"consistently":[152],"outperforms":[153,176],"competitive":[155],"baselines":[156],"terms":[158],"naturalness,":[160],"robustness":[161],"expressiveness":[163],"in-domain":[165],"Furthermore,":[170],"adversarial":[177],"learning":[178],"augmentation":[181],"addressing":[183],"problem.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}