{"id":"https://openalex.org/W4375869117","doi":"https://doi.org/10.1109/icassp49357.2023.10094994","title":"Unsupervised Pre-Training for Data-Efficient Text-to-Speech on Low Resource Languages","display_name":"Unsupervised Pre-Training for Data-Efficient Text-to-Speech on Low Resource Languages","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869117","doi":"https://doi.org/10.1109/icassp49357.2023.10094994"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5010111672","display_name":"Seongyeon Park","orcid":"https://orcid.org/0009-0007-3480-6626"},"institutions":[{"id":"https://openalex.org/I4210139352","display_name":"Hyundai Engineering (South Korea)","ror":"https://ror.org/04qgd6703","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210139352"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Seongyeon Park","raw_affiliation_strings":["CNAI,Seoul,Korea","CNAI, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"CNAI,Seoul,Korea","institution_ids":["https://openalex.org/I4210139352"]},{"raw_affiliation_string":"CNAI, Seoul, Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028920201","display_name":"Myungseo Song","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139352","display_name":"Hyundai Engineering (South Korea)","ror":"https://ror.org/04qgd6703","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210139352"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Myungseo Song","raw_affiliation_strings":["CNAI,Seoul,Korea","CNAI, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"CNAI,Seoul,Korea","institution_ids":["https://openalex.org/I4210139352"]},{"raw_affiliation_string":"CNAI, Seoul, Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086473903","display_name":"Bohyung Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139352","display_name":"Hyundai Engineering (South Korea)","ror":"https://ror.org/04qgd6703","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210139352"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bohyung Kim","raw_affiliation_strings":["CNAI,Seoul,Korea","CNAI, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"CNAI,Seoul,Korea","institution_ids":["https://openalex.org/I4210139352"]},{"raw_affiliation_string":"CNAI, Seoul, Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078114111","display_name":"Tae-Hyun Oh","orcid":"https://orcid.org/0000-0003-0468-1571"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]},{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]},{"id":"https://openalex.org/I4210120602","display_name":"Advanced Institute of Convergence Technology","ror":"https://ror.org/01w62yz22","country_code":"KR","type":"facility","lineage":["https://openalex.org/I139264467","https://openalex.org/I4210120602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tae-Hyun Oh","raw_affiliation_strings":["POSTECH,Dept. of EE and GSAI,Pohang,Korea","Institute for Convergence Research and Education in Advanced Technology, Yonsei University, Seoul, Korea","Dept. of EE and GSAI, POSTECH, Pohang, Korea"],"affiliations":[{"raw_affiliation_string":"POSTECH,Dept. of EE and GSAI,Pohang,Korea","institution_ids":["https://openalex.org/I123900574"]},{"raw_affiliation_string":"Institute for Convergence Research and Education in Advanced Technology, Yonsei University, Seoul, Korea","institution_ids":["https://openalex.org/I4210120602","https://openalex.org/I193775966"]},{"raw_affiliation_string":"Dept. of EE and GSAI, POSTECH, Pohang, Korea","institution_ids":["https://openalex.org/I123900574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010111672"],"corresponding_institution_ids":["https://openalex.org/I4210139352"],"apc_list":null,"apc_paid":null,"fwci":0.1748,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52423487,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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/T10860","display_name":"Speech and Audio Processing","score":0.9977999925613403,"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":0.8561660647392273},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6842154264450073},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5754510164260864},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5745173692703247},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5497274994850159},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5183397531509399},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5047610998153687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4991793632507324},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4973500072956085},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4617597758769989},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41964656114578247},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.17567351460456848}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8561660647392273},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6842154264450073},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5754510164260864},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5745173692703247},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5497274994850159},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5183397531509399},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5047610998153687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4991793632507324},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4973500072956085},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4617597758769989},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41964656114578247},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.17567351460456848},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2107860279","https://openalex.org/W2120847449","https://openalex.org/W2747874407","https://openalex.org/W2889028433","https://openalex.org/W2892620417","https://openalex.org/W2936774411","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W3016159759","https://openalex.org/W3096303254","https://openalex.org/W3096656254","https://openalex.org/W3100270690","https://openalex.org/W3161492781","https://openalex.org/W3161890269","https://openalex.org/W4223506691","https://openalex.org/W4224301045","https://openalex.org/W4225463329","https://openalex.org/W4283777098","https://openalex.org/W4289446300","https://openalex.org/W6631190155","https://openalex.org/W6736996214","https://openalex.org/W6743149223","https://openalex.org/W6755135894","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2348534359"],"abstract_inverted_index":{"Neural":[0],"text-to-speech":[1],"(TTS)":[2],"models":[3],"can":[4,47],"synthesize":[5],"natural":[6],"human":[7],"speech":[8,41],"when":[9],"trained":[10],"on":[11],"large":[12,39],"amounts":[13],"of":[14,52,119],"transcribed":[15,21,54],"speech.":[16],"How-ever,":[17],"collecting":[18],"such":[19],"large-scale":[20],"data":[22,55,103,110],"is":[23,70],"expensive.":[24],"This":[25],"paper":[26],"proposes":[27],"an":[28],"unsupervised":[29],"pre-training":[30],"method":[31,105,122],"for":[32,61],"a":[33,102],"sequence-to-sequence":[34],"TTS":[35,65],"model":[36,60,74,86],"by":[37],"leveraging":[38],"untranscribed":[40],"data.":[42],"With":[43],"our":[44,120],"pre-training,":[45],"we":[46,100],"remarkably":[48],"reduce":[49],"the":[50,59,62,73,85,109,117],"amount":[51],"paired":[53],"required":[56],"to":[57,71,75,87,131],"train":[58],"target":[63],"downstream":[64],"task.":[66],"The":[67,134],"main":[68],"idea":[69],"pre-train":[72],"reconstruct":[76],"de-warped":[77],"mel-spectrograms":[78],"from":[79],"warped":[80],"ones,":[81],"which":[82],"may":[83],"allow":[84],"learn":[88],"proper":[89],"temporal":[90],"assignment":[91],"relation":[92],"between":[93],"input":[94],"and":[95,136],"output":[96],"sequences.":[97],"In":[98],"addition,":[99],"propose":[101],"augmentation":[104],"that":[106],"further":[107],"improves":[108],"efficiency":[111],"in":[112,123],"finetuning.":[113],"We":[114],"empirically":[115],"demonstrate":[116],"effectiveness":[118],"proposed":[121],"low-resource":[124],"language":[125],"scenarios,":[126],"achieving":[127],"outstanding":[128],"performance":[129],"compared":[130],"competing":[132],"methods.":[133],"code":[135],"audio":[137],"samples":[138],"are":[139],"available":[140],"at:":[141],"https://github.com/cnaigithub/SpeechDewarping":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}