{"id":"https://openalex.org/W4206203111","doi":"https://doi.org/10.1109/o-cocosda202152914.2021.9660431","title":"Text-to-Speech Systems for Filipino Using Unit Selection and Deep Learning","display_name":"Text-to-Speech Systems for Filipino Using Unit Selection and Deep Learning","publication_year":2021,"publication_date":"2021-11-18","ids":{"openalex":"https://openalex.org/W4206203111","doi":"https://doi.org/10.1109/o-cocosda202152914.2021.9660431"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda202152914.2021.9660431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda202152914.2021.9660431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 24th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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/A5082507116","display_name":"Edsel Jedd Renovalles","orcid":null},"institutions":[{"id":"https://openalex.org/I87074743","display_name":"University of the Philippines Diliman","ror":"https://ror.org/03tbh6y23","country_code":"PH","type":"education","lineage":["https://openalex.org/I103911934","https://openalex.org/I87074743"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Edsel Jedd Renovalles","raw_affiliation_strings":["University of the Philippines Diliman, Electrical and Electronics Engineering Institute, Quezon City, Philippines"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of the Philippines Diliman, Electrical and Electronics Engineering Institute, Quezon City, Philippines","institution_ids":["https://openalex.org/I87074743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068297069","display_name":"Crisron Rudolf Lucas","orcid":null},"institutions":[{"id":"https://openalex.org/I87074743","display_name":"University of the Philippines Diliman","ror":"https://ror.org/03tbh6y23","country_code":"PH","type":"education","lineage":["https://openalex.org/I103911934","https://openalex.org/I87074743"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Crisron Rudolf Lucas","raw_affiliation_strings":["University of the Philippines Diliman, Electrical and Electronics Engineering Institute, Quezon City, Philippines"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of the Philippines Diliman, Electrical and Electronics Engineering Institute, Quezon City, Philippines","institution_ids":["https://openalex.org/I87074743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028150804","display_name":"Franz de Leon","orcid":null},"institutions":[{"id":"https://openalex.org/I87074743","display_name":"University of the Philippines Diliman","ror":"https://ror.org/03tbh6y23","country_code":"PH","type":"education","lineage":["https://openalex.org/I103911934","https://openalex.org/I87074743"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Franz de Leon","raw_affiliation_strings":["University of the Philippines Diliman, Electrical and Electronics Engineering Institute, Quezon City, Philippines"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of the Philippines Diliman, Electrical and Electronics Engineering Institute, Quezon City, Philippines","institution_ids":["https://openalex.org/I87074743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063576963","display_name":"Angelina Aquino","orcid":null},"institutions":[{"id":"https://openalex.org/I87074743","display_name":"University of the Philippines Diliman","ror":"https://ror.org/03tbh6y23","country_code":"PH","type":"education","lineage":["https://openalex.org/I103911934","https://openalex.org/I87074743"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Angelina Aquino","raw_affiliation_strings":["University of the Philippines Diliman, Electrical and Electronics Engineering Institute, Quezon City, Philippines"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of the Philippines Diliman, Electrical and Electronics Engineering Institute, Quezon City, Philippines","institution_ids":["https://openalex.org/I87074743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073753113","display_name":"Izza Jalandoni","orcid":null},"institutions":[{"id":"https://openalex.org/I87074743","display_name":"University of the Philippines Diliman","ror":"https://ror.org/03tbh6y23","country_code":"PH","type":"education","lineage":["https://openalex.org/I103911934","https://openalex.org/I87074743"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Izza Jalandoni","raw_affiliation_strings":["University of the Philippines Diliman, Electrical and Electronics Engineering Institute, Quezon City, Philippines"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of the Philippines Diliman, Electrical and Electronics Engineering Institute, Quezon City, Philippines","institution_ids":["https://openalex.org/I87074743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87074743"],"apc_list":null,"apc_paid":null,"fwci":0.1465,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.44746779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"2","issue":null,"first_page":"212","last_page":"217"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9926000237464905,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9922000169754028,"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/selection","display_name":"Selection (genetic algorithm)","score":0.7969428300857544},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7763587236404419},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.635930597782135},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.629692554473877},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.5378652215003967},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5074095129966736},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4977433979511261},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.4587097764015198},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.44285932183265686},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.4321237802505493},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14186632633209229},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06785938143730164}],"concepts":[{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.7969428300857544},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7763587236404419},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.635930597782135},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.629692554473877},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.5378652215003967},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5074095129966736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4977433979511261},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.4587097764015198},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44285932183265686},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.4321237802505493},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14186632633209229},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06785938143730164},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda202152914.2021.9660431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda202152914.2021.9660431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 24th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7300000190734863,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W90422898","https://openalex.org/W2018232658","https://openalex.org/W2312875274","https://openalex.org/W2341907140","https://openalex.org/W2598638573","https://openalex.org/W2964243274","https://openalex.org/W3118609936","https://openalex.org/W6703782078"],"related_works":["https://openalex.org/W3164858600","https://openalex.org/W3109498233","https://openalex.org/W2031768607","https://openalex.org/W4297798732","https://openalex.org/W4200068392","https://openalex.org/W4205278983","https://openalex.org/W3161890269","https://openalex.org/W4298324454","https://openalex.org/W2152669512","https://openalex.org/W3127598333"],"abstract_inverted_index":{"There":[0],"are":[1],"several":[2],"text-to-speech":[3],"(TTS)":[4],"systems":[5,70],"developed":[6],"and":[7,15,38,63,81,95,102,136,162],"published":[8],"for":[9,44,71,166],"Philippine":[10,45],"languages,":[11,46],"particularly":[12],"in":[13,133],"Filipino":[14],"Cebuano.":[16],"However,":[17],"there":[18],"is":[19],"still":[20],"a":[21,48,118],"need":[22],"to":[23,31,52,106,140,153,178],"improve":[24],"the":[25,32,65,92,98,108,126,134,145,148,155,169],"performance":[26,66,171],"of":[27,35,40,67,97,111,123,150,176],"existing":[28],"systems.":[29],"Due":[30],"limited":[33],"amount":[34],"linguistic":[36],"resources":[37],"lack":[39],"speech":[41],"data":[42,110,158,161],"available":[43],"developing":[47],"reliable":[49],"TTS":[50,69],"system":[51,101,116],"support":[53],"these":[54],"languages":[55],"becomes":[56],"difficult.":[57],"In":[58],"this":[59],"paper,":[60],"we":[61],"implement":[62],"evaluate":[64],"two":[68,75],"Filipino.":[72],"We":[73,87],"implemented":[74],"methods:":[76],"unit":[77,99,114],"selection":[78,100,115],"using":[79,85],"MaryTTS":[80],"deep":[82],"learning":[83],"approach":[84],"Tacotron-2.":[86,112],"tried":[88],"applying":[89],"modification":[90,129],"on":[91],"F0":[93,128],"contour":[94],"duration":[96],"used":[103],"voice":[104,151],"conversion":[105,152],"augment":[107],"training":[109,167],"The":[113],"achieved":[117],"mean":[119],"opinion":[120],"score":[121],"(MOS)":[122],"3.05,":[124],"however,":[125],"boundary-based":[127],"yielded":[130],"perceivable":[131],"distortions":[132],"output":[135],"requires":[137],"more":[138,142,164],"enhancements":[139],"become":[141],"effective.":[143],"On":[144],"other":[146],"hand,":[147],"use":[149],"transform":[154],"original":[156],"multi-speaker":[157],"into":[159],"single-speaker":[160],"producing":[163],"samples":[165],"boosted":[168],"Tacotron-2":[170],"from":[172],"an":[173],"overall":[174],"MOS":[175],"1.51":[177],"2.01.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
