Related papers: Unsupervised vocal dereverberation with diffusion-…

Visual acoustic matching (VAM) is pivotal for enhancing the immersive experience, and the task of dereverberation is effective in improving audio intelligibility. Existing methods treat each task independently, overlooking the inherent…

Diffusion models have been recently studied as powerful generative inverse problem solvers, owing to their high quality reconstructions and the ease of combining existing iterative solvers. However, most works focus on solving simple linear…

Diffusion-based generative models are a design framework that allows generating new images from processes analogous to those found in non-equilibrium thermodynamics. These models model the reversal of a physical diffusion process in which…

Audio inpainting seeks to restore missing segments in degraded recordings. Previous diffusion-based methods exhibit impaired performance when the missing region is large. We introduce the first approach that applies discrete diffusion over…

We present a supervised learning framework of training generative models for density estimation. Generative models, including generative adversarial networks, normalizing flows, variational auto-encoders, are usually considered as…

State-of-the-art under-determined audio source separation systems rely on supervised end-end training of carefully tailored neural network architectures operating either in the time or the spectral domain. However, these methods are…

We investigate the effectiveness of convolutive prediction, a novel formulation of linear prediction for speech dereverberation, for speaker separation in reverberant conditions. The key idea is to first use a deep neural network (DNN) to…

Generative diffusion models have emerged as leading models in speech and image generation. However, in order to perform well with a small number of denoising steps, a costly tuning of the set of noise parameters is needed. In this work, we…

Blind face restoration methods have shown remarkable performance, particularly when trained on large-scale synthetic datasets with supervised learning. These datasets are often generated by simulating low-quality face images with a…

Music source separation is focused on extracting distinct sonic elements from composite tracks. Historically, many methods have been grounded in supervised learning, necessitating labeled data, which is occasionally constrained in its…

We present a method to remove unknown convolutive noise introduced to speech by reverberations of recording environments, utilizing some amount of training speech data from the reverberant environment, and any available non-reverberant…

We propose self-diffusion, a novel framework for solving inverse problems without relying on pretrained generative models. Traditional diffusion-based approaches require training a model on a clean dataset to learn to reverse the forward…

Previous research on late-reverberation modeling has mainly focused on exponentially decaying room impulse responses, whereas methods for accurately modeling non-exponential reverberation remain challenging. This paper extends the…

Robust invisible watermarks are widely used to support copyright protection, content provenance, and accountability by embedding hidden signals designed to survive common post-processing operations. However, diffusion-based image editing…

Diffusion models have become central to various image editing tasks, yet they often fail to fully adhere to physical laws, particularly with effects like shadows, reflections, and occlusions. In this work, we address the challenge of…

Existing music generation models are mostly language-based, neglecting the frequency continuity property of notes, resulting in inadequate fitting of rare or never-used notes and thus reducing the diversity of generated samples. We argue…

Human body restoration plays a vital role in various applications related to the human body. Despite recent advances in general image restoration using generative models, their performance in human body restoration remains mediocre, often…

The problem of speech separation, also known as the cocktail party problem, refers to the task of isolating a single speech signal from a mixture of speech signals. Previous work on source separation derived an upper bound for the source…

This study presents a novel method for generating music visualisers using diffusion models, combining audio input with user-selected artwork. The process involves two main stages: image generation and video creation. First, music captioning…

Diffusion models exhibit impressive generative capabilities but are significantly impacted by exposure bias. In this paper, we make a key observation: the energy of predicted noisy samples in the reverse process continuously declines…