EXPRESSIVE TEXT TO SPEECH SYSTEM TO READ INDONESIA NOVEL BASED ON DEEP NEURAL NETWORK USING GLOBAL STYLE TOKEN AND TACOTRON 2
This research aims to construct an Expressive Text to Speech (TTS) system in the domain of Indonesia Language. Tacotron 2 is used in this study with Global Style Token (GST) as an additional feature and Parallel WaveGAN as a vocoder. Linguistic features are extracted from input text using Taco...
Saved in:
Main Author: | Azhar Dhiaulhaq, Moch. |
---|---|
Format: | Final Project |
Language: | Indonesia |
Online Access: | https://digilib.itb.ac.id/gdl/view/56159 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Institut Teknologi Bandung |
Language: | Indonesia |
Similar Items
-
POST-CONTROL PROSODY AND EMOTION FOR INDONESIA TEXT TO SPEECH SYSTEM
by: Azhar Dhiaulhaq, Moch -
An evaluation of tokenizers on domain specific text
by: Tao, Yuan
Published: (2022) -
Tokenism at the global level
by: Delos Reyes, Joy C.
Published: (2007) -
DeepStyle: User style embedding for authorship attribution of short texts
by: HU, Zhiqiang, et al.
Published: (2020) -
Neural talk: Text-to-speech synthesizer using neural networks
by: Go, Wilbert U., et al.
Published: (1995)