Despite being spoken by a large population of speakers worldwide, Cantonese is under-
resourced in terms of the data scale and diversity compared to other major languages. This …

This paper proposes a novel semi-supervised TTS framework, QS-TTS, to improve TTS
quality with lower supervised data requirements via Vector-Quantized Self-Supervised …

Aims and objectives: Previous research has revealed much about the syntactic and social
variables conditioning code-switching (ie, the alternation between two or more languages in …

Eye-tracking data in Chinese languages present unique challenges due to the non-
alphabetic and unspaced nature of the Chinese writing systems. This paper introduces the …

Cantonese-English is a low-resource language pair for machine translation (MT) studies,
despite the vast amount of English content publicly available online and the large amount of …

This study had the objective of exploring the parent–child interaction pattern during free
play. The current research examined parental utterances in terms of parents' linguistic …

The rapid evolution of large language models (LLMs) has transformed the competitive
landscape in natural language processing (NLP), particularly for English and other data-rich …

Heritage language speakers often feel discouraged from using their heritage language
because they are told they do not speak it well. This book offsets such views by investigating …

Counselling sessions have multiple stages, each with its themes and objectives. This study
aimed to apply Hidden Markov Models (HMMs) to analyse counselling sessions from Open …

This paper investigates the development and evaluation of machine translation models from
Cantonese to English (and backward), where we propose a novel approach to tackle low …