Language-queried audio source separation (LASS) is a new paradigm for computational
auditory scene analysis (CASA). LASS aims to separate a target sound from an audio …

Speech restoration aims to remove distortions in speech signals. Prior methods mainly focus
on a single type of distortion, such as speech denoising or dereverberation. However …

Audio denoising has been explored for decades using both traditional and deep learning-
based methods. However, these methods are still limited to either manually added artificial …

Deep learning techniques for separating audio into different sound sources face several
challenges. Standard architectures require training separate models for different types of …

Audio denoising is a task to improve the perceptual quality of noisy audio signals. There is
still residual noise after the denoising of noisy signals, which will affect the quality of audio …

We propose FedEnhance, an unsupervised federated learning (FL) approach for speech
enhancement and separation with non-IID distributed data across multiple clients. We …

Achieving high-performance audio denoising is still a challenging task in real-world
applications. Existing time-frequency methods often ignore the quality of generated …

Few-shot audio event detection is a task that detects the occurrence time of a novel sound
class given a few examples. In this work, we propose a system based on segment-level …

Nowadays, a common framework for weakly supervised sound event detection (WSSED) is
multiple instance learning (MIL). However, MIL directly optimizes the clip-level classification …

Few-shot bioacoustic event detection is a task that detects the occurrence time of a novel
sound given a few examples. Previous methods employ metric learning to build a latent …