Auditory Perception
Auditory perception research aims to understand how humans process and interpret sounds, focusing on bridging the gap between human experience and machine-based models of sound recognition. Current research emphasizes improving the accuracy and robustness of audio-language models, particularly addressing issues like object hallucination and the impact of noise, while also exploring novel architectures like transformers and generative models for audio reconstruction and enhancement. These advancements have implications for improving human-computer interaction, assistive technologies, and our fundamental understanding of the neural mechanisms underlying auditory processing.
Papers
Target Sound Extraction with Variable Cross-modality Clues
Chenda Li, Yao Qian, Zhuo Chen, Dongmei Wang, Takuya Yoshioka, Shujie Liu, Yanmin Qian, Michael Zeng
Autonomous Soundscape Augmentation with Multimodal Fusion of Visual and Participant-linked Inputs
Kenneth Ooi, Karn N. Watcharasupat, Bhan Lam, Zhen-Ting Ong, Woon-Seng Gan