Taiwanese Across Taiwan Corpus And Its Applications

Taiwanese across Taiwan (TAT) corpus is the first large-scale and publicly released Taiwanese speech corpus which represents the modern Taiwanese around Taiwan. This paper briefly reviews the TAT corpus and a corresponding parallel Chinese, Hàn-Lô-Tâi-bûn, Tai-Luo and Péh-ōe-jī lexicon and demonstra...

Full description

Saved in:
Bibliographic Details
Main Authors: Liao, Yuan-Fu, Tsay, Jane S., Kang, Peter, Khoo, Hui-Lu, Tan, Le-Kun, Chang, Li-Chen, Iunn, Un-Gian, Su, Huang-Lan, Thiann, Tsun-Guan, Tiun, Hak-Khiam, Liao, Su-Lian
Format: Conference Proceeding
Language:English
Subjects:
automatic speech recognition
speech synthesis
Taiwanese speech corpus
voice conversion
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Taiwanese across Taiwan (TAT) corpus is the first large-scale and publicly released Taiwanese speech corpus which represents the modern Taiwanese around Taiwan. This paper briefly reviews the TAT corpus and a corresponding parallel Chinese, Hàn-Lô-Tâi-bûn, Tai-Luo and Péh-ōe-jī lexicon and demonstrate some of their potential applications including ASR, TTS and voice conversion. The corresponding pretrained ASR and TTS models, sample model usage codes and training scripts will also be released. More information could be found on the Formosa Speech in the Wild website: https: //sites. google. com/nycu.edu.tw/fsw.
ISSN:2472-7695
DOI:10.1109/O-COCOSDA202257103.2022.9997977