iSpeak

Abstract

The proposed Cantonese Text to Speech project aims to address the lack of research and resources available for this underrepresented language. This project seeks to develop a high-quality TTS system for Cantonese that is both linguistically and culturally appropriate. One of the biggest challenges in this project is the lack of open-source data sets for Cantonese. In addition, Cantonese is a tonal and complex language, with a large number of characters and nuances that make it difficult to accurately capture in a speech synthesis system. The successful development of a Cantonese TTS system would have far-reaching benefits, which is crucial for the development in multifaceted fields, such as AI-based product development, voice assistant, etc.