Research Overview
At the AIRIS lab, we are at the forefront of redefining auditory experiences through cutting-edge research in immersive sound. Our work is dedicated to understanding and enhancing how humans perceive and interact with sound in three-dimensional spaces. By integrating advanced technologies such as artificial intelligence, augmented reality, and immersive sound rendering, we aim to better understand listeners’ perceptual and cognitive process for immersive sound and integrate spatial sound for holistic and realistic experience in a virtual space such as the metaverse.
Research Focus
Our research is currently focusing on the following four areas:
- Auditory Training: Developing gamified auditory training applications using augmented reality (AR) to enhance listening skills, particularly for individuals with hearing impairments. These applications aim to improve auditory selective attention, speech perception in noise, and sound localization abilities.
- Aural Heritage: Preserving cultural and historical soundscapes through virtual reality (VR) and augmented reality (AR). By integrating these immersive technologies, we create interactive experiences that allow users to engage with and appreciate aural heritage in new and meaningful ways.
- Immersive Audio AI: Developing artificial intelligence (AI) algorithms for generating 3D audio effects. This includes spatialization techniques such as room impulse response(RIR) generation and automatic panning.
- Immersive Recording and Playback: Exploring immersive recording and playback technologies, particularly focusing on binaural audio. Our research aims to enhance the realism and user preference for immersive audio experiences, ensuring high-quality sound reproduction that aligns with listeners' perceptual and cognitive processes.
