Related papers: CleanUNet 2: A Hybrid Speech Denoising Model on Wa…

Low-complexity speech enhancement on mobile phones is crucial in the era of 5G. Thus, focusing on handheld mobile phone communication scenario, based on power level difference (PLD) algorithm and lightweight U-Net, we propose PLD-guided…

Speech enhancement (SE) methods mainly focus on recovering clean speech from noisy input. In real-world speech communication, however, noises often exist in not only speaker but also listener environments. Although SE methods can suppress…

Taking inspiration from recent developments in visual generative tasks using diffusion models, we propose a method for end-to-end speech-driven video editing using a denoising diffusion model. Given a video of a talking person, and a…

Speech enhancement is challenging because of the diversity of background noise types. Most of the existing methods are focused on modelling the speech rather than the noise. In this paper, we propose a novel idea to model speech and noise…

The quality of audio recordings in outdoor environments is often degraded by the presence of wind. Mitigating the impact of wind noise on the perceptual quality of single-channel speech remains a significant challenge due to its…

Diffusion models have been shown to achieve natural-sounding enhancement of speech degraded by noise or reverberation. However, their simultaneous denoising and dereverberation capability has so far not been studied much, although this is…

Neural network-based speaker recognition has achieved significant improvement in recent years. A robust speaker representation learns meaningful knowledge from both hard and easy samples in the training set to achieve good performance.…

Accurately annotated ultrasonic images are vital components of a high-quality medical report. Hospitals often have strict guidelines on the types of annotations that should appear on imaging results. However, manually inspecting these…

Image denoising is a fundamental problem in computer vision and medical imaging. However, real-world images are often degraded by structured noise with strong anisotropic correlations that existing methods struggle to remove. Most…

Generative models in vision have seen rapid progress due to algorithmic improvements and the availability of high-quality image datasets. In this paper, we offer contributions in both these areas to enable similar progress in audio…

Most neural network speech enhancement models ignore speech production mathematical models by directly mapping Fourier transform spectrums or waveforms. In this work, we propose a neural source filter network for speech enhancement.…

Deep learning-based music source separation has gained a lot of interest in the last decades. Most of the existing methods operate with either spectrograms or waveforms. Spectrogram based models learn suitable masks for separating magnitude…

Point clouds obtained with 3D scanners or by image-based reconstruction techniques are often corrupted with significant amount of noise and outliers. Traditional methods for point cloud denoising largely rely on local surface fitting (e.g.,…

Speech super-resolution (SSR) aims to predict a high resolution (HR) speech signal from its low resolution (LR) corresponding part. Most neural SSR models focus on producing the final result in a noise-free environment by recovering the…

Speech enhancement systems are typically trained using pairs of clean and noisy speech. In audio-visual speech enhancement (AVSE), there is not as much ground-truth clean data available; most audio-visual datasets are collected in…

Low-dose computed tomography (LDCT) has become the technology of choice for diagnostic medical imaging, given its lower radiation dose compared to standard CT, despite increasing image noise and potentially affecting diagnostic accuracy. To…

Deep learning-based models have greatly advanced the performance of speech enhancement (SE) systems. However, two problems remain unsolved, which are closely related to model generalizability to noisy conditions: (1) mismatched noisy…

Recently, many deep learning based beamformers have been proposed for multi-channel speech separation. Nevertheless, most of them rely on extra cues known in advance, such as speaker feature, face image or directional information. In this…

In this work, we extend ClariNet (Ping et al., 2019), a fully end-to-end speech synthesis model (i.e., text-to-wave), to generate high-fidelity speech from multiple speakers. To model the unique characteristic of different voices, low…

Compared with traditional seismic noise attenuation algorithms that depend on signal models and their corresponding prior assumptions, removing noise with a deep neural network is trained based on a large training set, where the inputs are…