Research Areas
Generative Speech/Language Model
Our team aims to develop AI systems that understand and generate human-like speech and text, improving automated communication and exploring applications in assistive technologies and customer service.
Model Compression & Optimization
Our team aims to enhance deep learning models through compression and optimization techniques, reducing size and computational needs for use in resource-limited settings.
Multimodal Processing
Our team aims to enhance Multimodal Processing by developing systems that combine and interpret visual, auditory, and textual data to improve interaction and decision-making.
Speech Recognition/Synthesis
Our team is focused on advancing Speech Recognition and Synthesis to enhance human-machine interactions. We aim to develop systems that accurately understand and generate speech across various languages and dialects.
Natural Language Understanding
Our team focuses on enhancing Natural Language Understanding to better interpret human language. We aim to develop AI that comprehends context and nuanced meanings, enabling more accurate interactions.