Research Project Overview and Description
This project focuses on the computational modeling of phonetic and phonological acquisition to understand how linguistic knowledge is consolidated and transferred. By utilizing GPU-accelerated deep learning and machine learning techniques, researchers develop precise mathematical models to simulate language learning and representation. The study aims to uncover how human mono-lingual and bilingual learners derive structure and meaning from speech signals, bridging theoretical linguistics with modern natural language processing.
This project focuses on the computational modeling of phonetic and phonological acquisition to understand how linguistic knowledge is consolidated and transferred. By utilizing GPU-accelerated deep learning and machine learning techniques, researchers develop precise mathematical models to simulate language learning and representation. The study aims to uncover how human mono-lingual and bilingual learners derive structure and meaning from speech signals, bridging theoretical linguistics with modern natural language processing.
Research Outcome
The project successfully developed precise mathematical models to simulate how monolingual and bilingual learners derive structure and meaning from speech signals. By utilizing GPU-accelerated deep learning and machine learning techniques, the research provided a new methodological framework for bridging theoretical linguistics with modern natural language processing. These computational simulations have helped uncover how linguistic knowledge is consolidated and transferred, contributing to a deeper understanding of phonetic and phonological acquisition. The findings are expected to lead to peer-reviewed publications and serve as a foundation for further research into human-like speech processing and learning biases.
About the researchers
Frank Lihui Tan is a PhD student in the Department of Linguistics at the University of Hong Kong, specializing in the computational modeling of phonetic and phonological acquisition, sound representation learning, and linguistic knowledge transfer.
Dr. Youngah Do is an Associate Professor in the Department of Linguistics at the University of Hong Kong, who holds a PhD from MIT and researches language learnability and learning biases in both spoken and signed languages using experimental and computational methods. She is particularly recognized for her work on the preservation and technological innovation of Hong Kong Sign Language (HKSL).
Fund Source
N/A
For enquiries
please contact at atlabhku.hk