{"id":"https://openalex.org/W4206092705","doi":"https://doi.org/10.1109/ialp54817.2021.9675251","title":"End-to-end Indonesian Speech Synthesis Based On Transfer Learning And Alternate Training","display_name":"End-to-end Indonesian Speech Synthesis Based On Transfer Learning And Alternate Training","publication_year":2021,"publication_date":"2021-12-11","ids":{"openalex":"https://openalex.org/W4206092705","doi":"https://doi.org/10.1109/ialp54817.2021.9675251"},"language":"en","primary_location":{"id":"doi:10.1109/ialp54817.2021.9675251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp54817.2021.9675251","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 Asian Language Processing (IALP)","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/A5041966370","display_name":"Yu Lu","orcid":"https://orcid.org/0000-0002-8647-3014"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Lu","raw_affiliation_strings":["School of Information Science and Engineering, Yunnan University, Kunming, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Yunnan University, Kunming, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076764073","display_name":"Jian Yang","orcid":"https://orcid.org/0000-0003-0488-1514"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["School of Information Science and Engineering, Yunnan University, Kunming, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Yunnan University, Kunming, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016984773","display_name":"Ruolin Yang","orcid":"https://orcid.org/0000-0001-6241-6317"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruolin Yang","raw_affiliation_strings":["School of Information Science and Engineering, Yunnan University, Kunming, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Yunnan University, Kunming, China","institution_ids":["https://openalex.org/I189210763"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I189210763"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"30","last_page":"35"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9948999881744385,"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":0.9696999788284302,"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/naturalness","display_name":"Naturalness","score":0.8419257402420044},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8113830089569092},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7552427053451538},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7008225917816162},{"id":"https://openalex.org/keywords/indonesian","display_name":"Indonesian","score":0.5530169010162354},{"id":"https://openalex.org/keywords/psqm","display_name":"PSQM","score":0.517287015914917},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.48382750153541565},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.47817331552505493},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4464412331581116},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4278600811958313},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39114677906036377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36408793926239014},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.31913113594055176},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.298816978931427},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10590988397598267}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8419257402420044},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8113830089569092},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7552427053451538},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7008225917816162},{"id":"https://openalex.org/C2779207338","wikidata":"https://www.wikidata.org/wiki/Q9240","display_name":"Indonesian","level":2,"score":0.5530169010162354},{"id":"https://openalex.org/C108699837","wikidata":"https://www.wikidata.org/wiki/Q7120750","display_name":"PSQM","level":4,"score":0.517287015914917},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.48382750153541565},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.47817331552505493},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4464412331581116},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4278600811958313},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39114677906036377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36408793926239014},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31913113594055176},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.298816978931427},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10590988397598267},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp54817.2021.9675251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp54817.2021.9675251","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 Asian Language Processing (IALP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W202879582","https://openalex.org/W2078993594","https://openalex.org/W2107860279","https://openalex.org/W2111284386","https://openalex.org/W2112197391","https://openalex.org/W2150658333","https://openalex.org/W2176263492","https://openalex.org/W2546766702","https://openalex.org/W2598638573","https://openalex.org/W2610641545","https://openalex.org/W2611479983","https://openalex.org/W2619368999","https://openalex.org/W2777302760","https://openalex.org/W2912984712","https://openalex.org/W2942807473","https://openalex.org/W2952127920","https://openalex.org/W2963300588","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2991571120","https://openalex.org/W3016151052","https://openalex.org/W3033411150","https://openalex.org/W3129017987","https://openalex.org/W3133667170","https://openalex.org/W3133963484","https://openalex.org/W6670693114","https://openalex.org/W6685322675","https://openalex.org/W6765987481","https://openalex.org/W6770488218","https://openalex.org/W6778823374","https://openalex.org/W6791415481"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W1537411440","https://openalex.org/W2053531689","https://openalex.org/W4206092705"],"abstract_inverted_index":{"The":[0,124,162],"end-to-end":[1,80],"speech":[2,81,148,172],"synthesis":[3,11,49,82,149],"system":[4],"is":[5],"superior":[6],"to":[7,33,77,88,98,151],"traditional":[8],"statistical":[9],"parameter":[10],"methods":[12],"in":[13,47],"many":[14],"aspects":[15],"and":[16,42,65,90,116,170],"obviously":[17],"improves":[18],"the":[19,43,48,53,61,79,92,100,119,139,158,176,179],"naturalness":[20],"of":[21,55,60,63,69,102,144,157,164,178],"synthesized":[22],"speech,":[23,108],"but":[24],"it":[25,31],"still":[26],"needs":[27,32],"improvement.":[28],"For":[29],"example,":[30],"use":[34],"a":[35],"larger-scale":[36],"high-quality":[37],"text-speech":[38,133],"pairs":[39,134],"training":[40,114,122,136],"model,":[41,83],"cumulative":[44],"error":[45],"formed":[46],"process":[50],"will":[51],"affect":[52],"quality":[54],"long":[56,107,146],"speech.":[57],"In":[58],"view":[59],"characteristics":[62],"Indonesian":[64,86,132,145],"its":[66],"current":[67],"situation":[68],"low":[70],"resources,":[71],"this":[72,96,109],"paper":[73,110],"uses":[74,85],"English":[75],"corpus":[76,87],"pre-train":[78],"then":[84,117],"transfer":[89],"learn":[91],"model":[93],"parameters.":[94],"On":[95],"basis,":[97],"overcome":[99],"influence":[101],"accumulated":[103],"errors":[104],"on":[105],"synthetic":[106,171],"proposes":[111],"an":[112],"alternative":[113,121],"method":[115],"studies":[118],"optimal":[120],"scheme.":[123],"experimental":[125],"results":[126,163],"show":[127],"that":[128,156],"when":[129],"using":[130],"small-scale":[131],"as":[135],"data":[137],"sets,":[138],"mean":[140],"Mel":[141],"cepstral":[142],"distortion":[143],"sentences":[147],"decreases":[150],"17.54,":[152],"significantly":[153],"lower":[154],"than":[155],"baseline":[159],"Tacotron2":[160],"system.":[161],"codec":[165],"attention":[166],"alignment":[167],"coordinate":[168],"figure":[169],"recognition":[173],"also":[174],"confirm":[175],"effectiveness":[177],"proposed":[180],"method.":[181]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}