{"id":"https://openalex.org/W4416799587","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249124","title":"A Hybrid Attention Mechanism to Improve Tacotron 2 Performance for Indonesian Text-to-Speech Synthesis","display_name":"A Hybrid Attention Mechanism to Improve Tacotron 2 Performance for Indonesian Text-to-Speech Synthesis","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799587","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249124"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249124","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5120570679","display_name":"Angela Catherina","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113440","display_name":"Institut Teknologi Kalimantan","ror":"https://ror.org/01xcgh759","country_code":"ID","type":"education","lineage":["https://openalex.org/I4210113440"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Angela Catherina","raw_affiliation_strings":["Institut Teknologi Kalimantan,Department of Informatics,Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Teknologi Kalimantan,Department of Informatics,Indonesia","institution_ids":["https://openalex.org/I4210113440"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045527054","display_name":"Bima Prihasto","orcid":"https://orcid.org/0000-0001-8933-7563"},"institutions":[{"id":"https://openalex.org/I4210113440","display_name":"Institut Teknologi Kalimantan","ror":"https://ror.org/01xcgh759","country_code":"ID","type":"education","lineage":["https://openalex.org/I4210113440"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Bima Prihasto","raw_affiliation_strings":["Institut Teknologi Kalimantan,Department of Informatics,Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Teknologi Kalimantan,Department of Informatics,Indonesia","institution_ids":["https://openalex.org/I4210113440"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060594044","display_name":"Boby Mugi Pratama","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113440","display_name":"Institut Teknologi Kalimantan","ror":"https://ror.org/01xcgh759","country_code":"ID","type":"education","lineage":["https://openalex.org/I4210113440"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Boby Mugi Pratama","raw_affiliation_strings":["Institut Teknologi Kalimantan,Department of Informatics,Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Teknologi Kalimantan,Department of Informatics,Indonesia","institution_ids":["https://openalex.org/I4210113440"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106664802","display_name":"Li\u2010Wei Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Li-Wei Kang","raw_affiliation_strings":["National Taiwan Normal University,Department of Electrical Engineering,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Department of Electrical Engineering,Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029325015","display_name":"Jia\u2010Ching Wang","orcid":"https://orcid.org/0000-0003-0024-6732"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jia-Ching Wang","raw_affiliation_strings":["National Central University,Department of Computer Science and Information Engineering,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Central University,Department of Computer Science and Information Engineering,Taiwan","institution_ids":["https://openalex.org/I22265921"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17657189,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"579","last_page":"582"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9100000262260437,"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":0.9100000262260437,"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/T11448","display_name":"Face recognition and analysis","score":0.00860000029206276,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T13194","display_name":"ICT in Developing Communities","score":0.0052999998442828655,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8906999826431274},{"id":"https://openalex.org/keywords/indonesian","display_name":"Indonesian","score":0.781499981880188},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.6499000191688538},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5250999927520752},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5004000067710876},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.42570000886917114}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8906999826431274},{"id":"https://openalex.org/C2779207338","wikidata":"https://www.wikidata.org/wiki/Q9240","display_name":"Indonesian","level":2,"score":0.781499981880188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7432000041007996},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.6499000191688538},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5450000166893005},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5250999927520752},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5004000067710876},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4447000026702881},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.42570000886917114},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4205999970436096},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3840999901294708},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3287000060081482},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.322299987077713},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.26930001378059387},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.2590000033378601}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249124","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1570629387","https://openalex.org/W2127571359","https://openalex.org/W2130596350","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W4200300291","https://openalex.org/W4372260612"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,40,63],"speech":[4,125],"synthesis":[5],"system":[6,59],"for":[7,31,134],"the":[8,12,115],"Indonesian":[9,32,65],"language":[10],"using":[11,87],"Tacotron":[13,20],"2":[14,21],"architecture":[15],"and":[16,47,54,80,84,90,123,129],"HiFi-GAN":[17],"vocoder.":[18],"While":[19],"has":[22],"demonstrated":[23],"strong":[24],"performance":[25,105],"in":[26,69,137],"high-resource":[27],"languages,":[28],"adapting":[29],"it":[30],"remains":[33],"underexplored.":[34],"To":[35],"address":[36],"this,":[37],"we":[38],"propose":[39],"hybrid":[41,117],"attention":[42,49,109,118],"mechanism":[43,119],"that":[44,114],"combines":[45],"location-sensitive":[46],"content-based":[48],"to":[50],"improve":[51],"alignment":[52,121],"accuracy":[53],"convergence":[55],"during":[56],"training.":[57],"The":[58],"is":[60,95,106],"trained":[61],"on":[62],"custom":[64],"audiobook":[66],"dataset":[67],"prepared":[68],"LJSpeech":[70],"format.":[71],"We":[72],"compare":[73],"several":[74],"model":[75,104],"variants,":[76],"including":[77],"versions":[78],"with":[79,126],"without":[81],"phoneme":[82],"conversion,":[83],"evaluate":[85],"them":[86],"both":[88],"subjective":[89],"objective":[91],"metrics.":[92],"Speech":[93],"quality":[94],"assessed":[96],"through":[97],"Mean":[98],"Opinion":[99],"Score":[100],"(MOS)":[101],"ratings,":[102],"while":[103],"evaluated":[107],"via":[108],"weight":[110],"visualization.":[111],"Results":[112],"show":[113],"proposed":[116],"accelerates":[120],"learning":[122],"produces":[124],"improved":[127],"naturalness":[128],"intelligibility,":[130],"confirming":[131],"its":[132],"effectiveness":[133],"low-resource":[135],"TTS":[136],"Indonesian.":[138]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}