Published multiple papers at IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) and INTERSPEECH, covering topics like zero-shot learning for speech recognition, enhanced-time domain monaural speech separation, robust speech recognition, low-resource keyword spotting, and more.
Research Experience
Working as a Speech Algorithm Engineer, focusing on research domains such as foundational models, automatic speech recognition (ASR), self-supervised learning, efficient tuning of large-scale models, speech synthesis, spoken dialogue, and retrieval-augmented generation.
Education
Completed master's and undergraduate studies in Statistics and Economics at the National University of Singapore (NUS). Currently pursuing a PhD in speech modelling at Nanyang Technological University (NTU), under the guidance of Prof. Eng-Siong Chng (NTU) and Dr. Bin Ma (Alibaba DAMO Academy).
Background
An enthusiastic artificial intelligence researcher with a strong curiosity to explore multiple areas, including multi-modal machine understanding, recognition, and generation. Passionate about advancing AI to enhance functionality and develop purposeful solutions that better serve users.