Audio Domain

Computer audition, the field of using machines to understand sound, aims to develop robust and efficient systems for various audio-related tasks. Current research focuses on improving audio enhancement techniques, particularly for noisy environments, leveraging foundation models for multi-task learning, and exploring self-supervised learning methods using architectures like transformers and diffusion models to learn effective audio representations from unlabeled data. These advancements are crucial for applications ranging from speech recognition and environmental monitoring to healthcare and creative audio technologies, driving significant progress in both the theoretical understanding and practical applications of audio processing.

Papers