{"id":"https://openalex.org/W4402137125","doi":"https://doi.org/10.3126/kjse.v8i1.69276","title":"Nepali Text-to-Speech Synthesis Using Tacotron2 and WaveGlow","display_name":"Nepali Text-to-Speech Synthesis Using Tacotron2 and WaveGlow","publication_year":2024,"publication_date":"2024-09-02","ids":{"openalex":"https://openalex.org/W4402137125","doi":"https://doi.org/10.3126/kjse.v8i1.69276"},"language":"en","primary_location":{"id":"doi:10.3126/kjse.v8i1.69276","doi":"https://doi.org/10.3126/kjse.v8i1.69276","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3126/kjse.v8i1.69276","pdf_url":"https://www.nepjol.info/index.php/kjse/article/download/69276/52873","source":{"id":"https://openalex.org/S5406978294","display_name":"KEC Journal of Science and Engineering","issn_l":"2091-2919","issn":["2091-2919"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"KEC Journal of Science and Engineering","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.nepjol.info/index.php/kjse/article/download/69276/52873","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106934336","display_name":"Ashma Rai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I155028946","display_name":"Tribhuvan University","ror":"https://ror.org/02rg1r889","country_code":"NP","type":"education","lineage":["https://openalex.org/I155028946"]},{"id":"https://openalex.org/I4405284132","display_name":"Institute of Engineering Thapathali Campus","ror":"https://ror.org/02zdzt011","country_code":"NP","type":"education","lineage":["https://openalex.org/I155028946","https://openalex.org/I4210129773","https://openalex.org/I4405284132"]}],"countries":["NP"],"is_corresponding":false,"raw_author_name":"Ashma Rai","raw_affiliation_strings":["\u00b3Dept of Electronics and Computer Engineering , Thapathali Campus , IOE , TU ,","Dept of Electronics, Communication & Information Engineering, Kathmandu Engineering College,","\u00b2Dept of Electronics and Computer Engineering, Thapathali Campus, IOE, TU,","\u00b3Dept of Electronics and Computer Engineering, Thapathali Campus, IOE, TU,","\u00b9Dept of Electronics and Computer Engineering, Thapathali Campus, IOE, TU,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00b3Dept of Electronics and Computer Engineering , Thapathali Campus , IOE , TU ,","institution_ids":["https://openalex.org/I155028946","https://openalex.org/I4405284132"]},{"raw_affiliation_string":"Dept of Electronics, Communication & Information Engineering, Kathmandu Engineering College,","institution_ids":[]},{"raw_affiliation_string":"\u00b2Dept of Electronics and Computer Engineering, Thapathali Campus, IOE, TU,","institution_ids":["https://openalex.org/I155028946","https://openalex.org/I4405284132"]},{"raw_affiliation_string":"\u00b3Dept of Electronics and Computer Engineering, Thapathali Campus, IOE, TU,","institution_ids":["https://openalex.org/I155028946","https://openalex.org/I4405284132"]},{"raw_affiliation_string":"\u00b9Dept of Electronics and Computer Engineering, Thapathali Campus, IOE, TU,","institution_ids":["https://openalex.org/I155028946","https://openalex.org/I4405284132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106934337","display_name":"Shikshya Shiwakoti","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I155028946","display_name":"Tribhuvan University","ror":"https://ror.org/02rg1r889","country_code":"NP","type":"education","lineage":["https://openalex.org/I155028946"]},{"id":"https://openalex.org/I4405284132","display_name":"Institute of Engineering Thapathali Campus","ror":"https://ror.org/02zdzt011","country_code":"NP","type":"education","lineage":["https://openalex.org/I155028946","https://openalex.org/I4210129773","https://openalex.org/I4405284132"]}],"countries":["NP"],"is_corresponding":false,"raw_author_name":"Shikshya Shiwakoti","raw_affiliation_strings":["\u00b3Dept of Electronics and Computer Engineering , Thapathali Campus , IOE , TU ,","Dept of Electronics, Communication & Information Engineering, Kathmandu Engineering College,","\u00b2Dept of Electronics and Computer Engineering, Thapathali Campus, IOE, TU,","\u00b3Dept of Electronics and Computer Engineering, Thapathali Campus, IOE, TU,","\u00b9Dept of Electronics and Computer Engineering, Thapathali Campus, IOE, TU,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00b3Dept of Electronics and Computer Engineering , Thapathali Campus , IOE , TU ,","institution_ids":["https://openalex.org/I155028946","https://openalex.org/I4405284132"]},{"raw_affiliation_string":"Dept of Electronics, Communication & Information Engineering, Kathmandu Engineering College,","institution_ids":[]},{"raw_affiliation_string":"\u00b2Dept of Electronics and Computer Engineering, Thapathali Campus, IOE, TU,","institution_ids":["https://openalex.org/I155028946","https://openalex.org/I4405284132"]},{"raw_affiliation_string":"\u00b3Dept of Electronics and Computer Engineering, Thapathali Campus, IOE, TU,","institution_ids":["https://openalex.org/I155028946","https://openalex.org/I4405284132"]},{"raw_affiliation_string":"\u00b9Dept of Electronics and Computer Engineering, Thapathali Campus, IOE, TU,","institution_ids":["https://openalex.org/I155028946","https://openalex.org/I4405284132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106934338","display_name":"Swostika Basukala","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I155028946","display_name":"Tribhuvan University","ror":"https://ror.org/02rg1r889","country_code":"NP","type":"education","lineage":["https://openalex.org/I155028946"]},{"id":"https://openalex.org/I4405284132","display_name":"Institute of Engineering Thapathali Campus","ror":"https://ror.org/02zdzt011","country_code":"NP","type":"education","lineage":["https://openalex.org/I155028946","https://openalex.org/I4210129773","https://openalex.org/I4405284132"]}],"countries":["NP"],"is_corresponding":false,"raw_author_name":"Swostika Basukala","raw_affiliation_strings":["\u00b2Dept of Electronics and Computer Engineering , Thapathali Campus , IOE , TU ,","\u00b9Dept of Electronics and Computer Engineering , Thapathali Campus , IOE , TU ,","Dept of Electronics, Communication & Information Engineering, Kathmandu Engineering College,","\u00b2Dept of Electronics and Computer Engineering, Thapathali Campus, IOE, TU,","\u00b3Dept of Electronics and Computer Engineering, Thapathali Campus, IOE, TU,","\u00b9Dept of Electronics and Computer Engineering, Thapathali Campus, IOE, TU,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00b2Dept of Electronics and Computer Engineering , Thapathali Campus , IOE , TU ,","institution_ids":["https://openalex.org/I155028946","https://openalex.org/I4405284132"]},{"raw_affiliation_string":"\u00b9Dept of Electronics and Computer Engineering , Thapathali Campus , IOE , TU ,","institution_ids":["https://openalex.org/I155028946","https://openalex.org/I4405284132"]},{"raw_affiliation_string":"Dept of Electronics, Communication & Information Engineering, Kathmandu Engineering College,","institution_ids":[]},{"raw_affiliation_string":"\u00b2Dept of Electronics and Computer Engineering, Thapathali Campus, IOE, TU,","institution_ids":["https://openalex.org/I155028946","https://openalex.org/I4405284132"]},{"raw_affiliation_string":"\u00b3Dept of Electronics and Computer Engineering, Thapathali Campus, IOE, TU,","institution_ids":["https://openalex.org/I155028946","https://openalex.org/I4405284132"]},{"raw_affiliation_string":"\u00b9Dept of Electronics and Computer Engineering, Thapathali Campus, IOE, TU,","institution_ids":["https://openalex.org/I155028946","https://openalex.org/I4405284132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107234713","display_name":"Suramya Sharma Dahal","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I155028946","display_name":"Tribhuvan University","ror":"https://ror.org/02rg1r889","country_code":"NP","type":"education","lineage":["https://openalex.org/I155028946"]},{"id":"https://openalex.org/I4405284132","display_name":"Institute of Engineering Thapathali Campus","ror":"https://ror.org/02zdzt011","country_code":"NP","type":"education","lineage":["https://openalex.org/I155028946","https://openalex.org/I4210129773","https://openalex.org/I4405284132"]}],"countries":["NP"],"is_corresponding":false,"raw_author_name":"Suramya Sharma Dahal","raw_affiliation_strings":["Associate Professor, Dept of Electronics, Communication & Information Engineering , Kathmandu Engineering College ,","Dept of Electronics, Communication & Information Engineering, Kathmandu Engineering College,","\u00b2Dept of Electronics and Computer Engineering, Thapathali Campus, IOE, TU,","\u00b3Dept of Electronics and Computer Engineering, Thapathali Campus, IOE, TU,","\u00b9Dept of Electronics and Computer Engineering, Thapathali Campus, IOE, TU,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Associate Professor, Dept of Electronics, Communication & Information Engineering , Kathmandu Engineering College ,","institution_ids":[]},{"raw_affiliation_string":"Dept of Electronics, Communication & Information Engineering, Kathmandu Engineering College,","institution_ids":[]},{"raw_affiliation_string":"\u00b2Dept of Electronics and Computer Engineering, Thapathali Campus, IOE, TU,","institution_ids":["https://openalex.org/I155028946","https://openalex.org/I4405284132"]},{"raw_affiliation_string":"\u00b3Dept of Electronics and Computer Engineering, Thapathali Campus, IOE, TU,","institution_ids":["https://openalex.org/I155028946","https://openalex.org/I4405284132"]},{"raw_affiliation_string":"\u00b9Dept of Electronics and Computer Engineering, Thapathali Campus, IOE, TU,","institution_ids":["https://openalex.org/I155028946","https://openalex.org/I4405284132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10245279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":"1","first_page":"103","last_page":"109"},"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/T10860","display_name":"Speech and Audio Processing","score":0.0,"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/T10863","display_name":"Voice and Speech Disorders","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/tacotron2","display_name":"Tacotron2","score":0.9800000190734863},{"id":"https://openalex.org/keywords/waveglow","display_name":"WaveGlow","score":1.0},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.8320000171661377},{"id":"https://openalex.org/keywords/model-adaptation","display_name":"model adaptation","score":0.5329999923706055},{"id":"https://openalex.org/keywords/spectrogram-generation","display_name":"spectrogram generation","score":0.9190000295639038},{"id":"https://openalex.org/keywords/vocoder","display_name":"vocoder","score":0.7149999737739563},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.8579999804496765},{"id":"https://openalex.org/keywords/text-normalization","display_name":"text normalization","score":0.574999988079071},{"id":"https://openalex.org/keywords/text-cleaning","display_name":"text cleaning","score":0.5509999990463257}],"concepts":[{"id":"https://openalex.org/C2780068402","wikidata":"https://www.wikidata.org/wiki/Q33823","display_name":"Nepali","level":2,"score":0.8750810027122498},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5578763484954834},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5250025987625122},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5076037645339966},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41441023349761963},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38367241621017456},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32632094621658325},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.16430747509002686}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3126/kjse.v8i1.69276","doi":"https://doi.org/10.3126/kjse.v8i1.69276","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3126/kjse.v8i1.69276","pdf_url":"https://www.nepjol.info/index.php/kjse/article/download/69276/52873","source":{"id":"https://openalex.org/S5406978294","display_name":"KEC Journal of Science and Engineering","issn_l":"2091-2919","issn":["2091-2919"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"KEC Journal of Science and Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3126/kjse.v8i1.69276","doi":"https://doi.org/10.3126/kjse.v8i1.69276","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3126/kjse.v8i1.69276","pdf_url":"https://www.nepjol.info/index.php/kjse/article/download/69276/52873","source":{"id":"https://openalex.org/S5406978294","display_name":"KEC Journal of Science and Engineering","issn_l":"2091-2919","issn":["2091-2919"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"KEC Journal of Science and Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.4300000071525574}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402137125.pdf","grobid_xml":"https://content.openalex.org/works/W4402137125.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2150658333","https://openalex.org/W2519091744","https://openalex.org/W2591927543","https://openalex.org/W2594721751","https://openalex.org/W2898847420","https://openalex.org/W2901997113","https://openalex.org/W2964243274","https://openalex.org/W4298289240"],"related_works":["https://openalex.org/W3022894621","https://openalex.org/W2091393109","https://openalex.org/W2571496589","https://openalex.org/W4319659831","https://openalex.org/W3209169650","https://openalex.org/W2778576746","https://openalex.org/W1513420593","https://openalex.org/W2728473837","https://openalex.org/W2567215502","https://openalex.org/W127416991"],"abstract_inverted_index":{"This":[0],"research":[1],"paper":[2],"presents":[3],"the":[4,40,49,59,103,123],"development":[5],"of":[6,39,51,61,83,145],"a":[7,52,62,78,93,142],"Nepali":[8,79,94,146],"Text-to-Speech":[9,53],"(TTS)":[10,54],"system":[11,81],"under":[12,87],"low-resource":[13,88],"conditions":[14],"by":[15,44],"adapting":[16],"pre-trained":[17,63,104],"English":[18,64],"Tacotron2":[19,23,65,105],"and":[20,30,67,155],"WaveGlow":[21,31,68],"models.":[22],"has":[24,32],"been":[25,33],"utilized":[26,120],"for":[27,35,109,141],"spectrogram":[28,110,124],"generation,":[29],"employed":[34],"vocoding,":[36],"with":[37,92,98],"recognition":[38],"pivotal":[41],"role":[42],"played":[43],"these":[45],"components":[46],"in":[47,138],"determining":[48],"efficacy":[50],"system.":[55],"Our":[56],"approach":[57],"entails":[58],"adaptation":[60],"model":[66,106,135],"architecture":[69],"to":[70,76,121,149],"Nepali,":[71],"leveraging":[72],"limited":[73],"data":[74],"resources":[75],"craft":[77],"TTS":[80],"capable":[82],"producing":[84],"natural-sounding":[85],"output":[86],"conditions.":[89],"Through":[90],"fine-tuning":[91],"text":[95,153],"corpus":[96],"aligned":[97],"its":[99],"corresponding":[100],"audio":[101,116,140],"dataset,":[102],"is":[107,119,130],"optimized":[108],"generation.":[111],"Subsequently,":[112],"WaveGlow,":[113],"our":[114,134],"chosen":[115],"synthesis":[117],"model,":[118],"convert":[122],"representations":[125],"into":[126],"audible":[127],"waveforms.":[128],"It":[129],"worth":[131],"noting":[132],"that":[133],"exhibits":[136],"limitations":[137],"synthesizing":[139],"restricted":[143],"subset":[144],"texts,":[147],"attributed":[148],"challenges":[150],"stemming":[151],"from":[152],"cleaning":[154],"normalization":[156],"inadequacies.":[157]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-10T00:00:00"}
