{"id":"https://openalex.org/W3016151052","doi":"https://doi.org/10.1109/icassp40776.2020.9054681","title":"Teacher-Student Training For Robust Tacotron-Based TTS","display_name":"Teacher-Student Training For Robust Tacotron-Based TTS","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016151052","doi":"https://doi.org/10.1109/icassp40776.2020.9054681","mag":"3016151052"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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":["Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University, China","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/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Berrak Sisman","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100642253","display_name":"Jingdong Li","orcid":"https://orcid.org/0000-0003-2335-6280"},"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":"Jingdong Li","raw_affiliation_strings":["Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014372166","display_name":"Feilong Bao","orcid":"https://orcid.org/0000-0001-7312-1629"},"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":"Feilong Bao","raw_affiliation_strings":["Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"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":["Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University, 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"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9972000122070312,"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":0.9965000152587891,"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/computer-science","display_name":"Computer science","score":0.7991876006126404},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6673327684402466},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5997296571731567},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5712389945983887},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5407786965370178},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5195453763008118},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.513587474822998},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5061120390892029},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.45709389448165894},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4512462317943573},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4137350618839264},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08833667635917664},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08401066064834595}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7991876006126404},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6673327684402466},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5997296571731567},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5712389945983887},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5407786965370178},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5195453763008118},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.513587474822998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5061120390892029},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.45709389448165894},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4512462317943573},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4137350618839264},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08833667635917664},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08401066064834595},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8600000143051147}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W2102003408","https://openalex.org/W2111284386","https://openalex.org/W2112197391","https://openalex.org/W2120847449","https://openalex.org/W2163605009","https://openalex.org/W2174424190","https://openalex.org/W2176263492","https://openalex.org/W2604184139","https://openalex.org/W2739879705","https://openalex.org/W2767052532","https://openalex.org/W2786868129","https://openalex.org/W2790783922","https://openalex.org/W2798951647","https://openalex.org/W2889026195","https://openalex.org/W2889028433","https://openalex.org/W2889064624","https://openalex.org/W2892734764","https://openalex.org/W2911340057","https://openalex.org/W2941094131","https://openalex.org/W2942807473","https://openalex.org/W2946200149","https://openalex.org/W2963248296","https://openalex.org/W2963609956","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2970730223","https://openalex.org/W2972595148","https://openalex.org/W2972702018","https://openalex.org/W2972789651","https://openalex.org/W2972951102","https://openalex.org/W2985308740","https://openalex.org/W3012404734","https://openalex.org/W3025182306","https://openalex.org/W4395704439","https://openalex.org/W6621543089","https://openalex.org/W6684191040","https://openalex.org/W6685322675","https://openalex.org/W6749025659","https://openalex.org/W6763832098","https://openalex.org/W6865583292"],"related_works":["https://openalex.org/W2171218219","https://openalex.org/W1972271943","https://openalex.org/W2150410159","https://openalex.org/W3150905897","https://openalex.org/W4327525404","https://openalex.org/W4287185323","https://openalex.org/W1520183331","https://openalex.org/W2099889858","https://openalex.org/W2168175994","https://openalex.org/W2283583712"],"abstract_inverted_index":{"While":[0],"neural":[1],"end-to-end":[2],"text-to-speech":[3],"(TTS)":[4],"is":[5,146],"superior":[6],"to":[7,25,73,91,122],"conventional":[8],"statistical":[9],"methods":[10],"in":[11,18,44,71,167],"many":[12],"ways,":[13],"the":[14,19,34,37,74,92,112,115,124,131,134,138,142,159],"exposure":[15,29],"bias":[16,30],"problem":[17,31],"autoregressive":[20],"models":[21],"remains":[22],"an":[23],"issue":[24],"be":[26],"resolved.":[27],"The":[28],"arises":[32],"from":[33,141],"mismatch":[35],"between":[36],"training":[38,60,155],"and":[39,169],"inference":[40],"process,":[41],"that":[42,94,145,152],"results":[43],"unpredictable":[45],"performance":[46],"for":[47,62,162],"out-of-domain":[48,163],"test":[49,164],"data":[50,165],"at":[51],"run-time.":[52],"To":[53],"overcome":[54],"this,":[55],"we":[56],"propose":[57],"a":[58,67,81,97,107],"teacher-student":[59],"scheme":[61,156],"Tacotron-based":[63],"TTS":[64,83],"by":[65,85],"introducing":[66],"distillation":[68,132],"loss":[69,76],"function":[70],"addition":[72],"feature":[75],"function.":[77],"We":[78,100],"first":[79],"train":[80,102],"Tacotron2-based":[82,104],"model":[84,105,136],"always":[86],"providing":[87],"natural":[88],"speech":[89,117],"frames":[90,118],"decoder,":[93],"serves":[95],"as":[96,106,119],"teacher":[98,143],"model.":[99],"then":[101],"another":[103],"student":[108,135],"model,":[109,144],"of":[110],"which":[111],"decoder":[113,125],"takes":[114],"predicted":[116],"input,":[120],"similar":[121],"how":[123],"works":[126],"during":[127],"run-time":[128],"inference.":[129],"With":[130],"loss,":[133],"learns":[137],"output":[139],"probabilities":[140],"called":[147],"knowledge":[148],"distillation.":[149],"Experiments":[150],"show":[151],"our":[153],"proposed":[154],"consistently":[157],"improves":[158],"voice":[160],"quality":[161],"both":[166],"Chinese":[168],"English":[170],"systems.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":15}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}