{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:07:53Z","timestamp":1764400073679,"version":"3.46.0"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249124","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"579-582","source":"Crossref","is-referenced-by-count":0,"title":["A Hybrid Attention Mechanism to Improve Tacotron 2 Performance for Indonesian Text-to-Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Angela","family":"Catherina","sequence":"first","affiliation":[{"name":"Institut Teknologi Kalimantan,Department of Informatics,Indonesia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bima","family":"Prihasto","sequence":"additional","affiliation":[{"name":"Institut Teknologi Kalimantan,Department of Informatics,Indonesia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boby Mugi","family":"Pratama","sequence":"additional","affiliation":[{"name":"Institut Teknologi Kalimantan,Department of Informatics,Indonesia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li-Wei","family":"Kang","sequence":"additional","affiliation":[{"name":"National Taiwan Normal University,Department of Electrical Engineering,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia-Ching","family":"Wang","sequence":"additional","affiliation":[{"name":"National Central University,Department of Computer Science and Information Engineering,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2010.5606343"},{"issue":"9","key":"ref2","first-page":"12","article-title":"A review of concatenative text to speech synthesis","volume":"3","author":"Hande","year":"2014","journal-title":"Int. J. Latest Technol. Eng. Manag. Appl. Sci. IJLTEMAS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref5","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511816338"},{"key":"ref7","article-title":"An overview of text-to-speech systems and media applications","author":"Hasanabadi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"A survey on recent approaches for natural language processing in low-resource scenarios","author":"Hedderich","year":"2020","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5296\/ijele.v1i3.3892"},{"key":"ref10","article-title":"Attention-based models for speech recognition","volume":"28","author":"Chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014","journal-title":"arXiv preprint"},{"key":"ref12","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03958"},{"issue":"4","key":"ref14","first-page":"650","article-title":"Mos and pair comparison combined methods for quality evaluation of text-to-speech systems","volume":"82","author":"Salza","year":"1996","journal-title":"Acta Acustica united with Acustica"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097248"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249124.pdf?arnumber=11249124","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:05:54Z","timestamp":1764399954000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249124\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249124","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}