AN Expressive Text To Speech System for Sinhala Language

Dias, Danoja

dc.contributor.author	Dias, Danoja
dc.date.accessioned	2023-01-23T04:08:41Z
dc.date.available	2023-01-23T04:08:41Z
dc.date.issued	2022
dc.identifier.citation	Dias, Danoja (2022) AN Expressive Text To Speech System for Sinhala Language. MSc. Dissertation, Informatics Institute of Technology	en_US
dc.identifier.issn	20200092
dc.identifier.uri	http://dlib.iit.ac.lk/xmlui/handle/123456789/1500
dc.description.abstract	This research attempts to investigate creating Text-To-Speech (TTS) System for Low Resource Sinhala Language using FastSpeech2. This project uses already available TTS datasets for the Sinhala Language. This research updates the existing open-source pronunciation dictionary by adding approximately 10000 new words with their pronunciations. New Montreal Forced Aligner (MFA) models, which were not available for the Sinhala Language, were created to do the forced alignments for this research. The evaluations were done with 20 native speakers to evaluate and calculate the MOS values. The experiments with FastSpeech2 have positive results with a MOS value of 3.35 ± 0.08	en_US
dc.language.iso	en	en_US
dc.subject	text-to-speech	en_US
dc.subject	linguistic resources	en_US
dc.title	AN Expressive Text To Speech System for Sinhala Language	en_US
dc.type	Thesis	en_US