Related papers: EDMSound: Spectrogram Based Diffusion Models for E…

Diffusion models have established themselves as the de facto primary paradigm in visual generative modeling, revolutionizing the field through remarkable success across various diverse applications ranging from high-quality image synthesis…

The goal of speech enhancement (SE) is to eliminate the background interference from the noisy speech signal. Generative models such as diffusion models (DM) have been applied to the task of SE because of better generalization in unseen…

Symbolic music generation is a challenging task in multimedia generation, involving long sequences with hierarchical temporal structures, long-range dependencies, and fine-grained local details. Though recent diffusion-based models produce…

Recently, environment reconstruction (ER) in integrated sensing and communication (ISAC) systems has emerged as a promising approach for achieving high-resolution environmental perception. However, the initial results obtained from ISAC…

Recent progress in diffusion-based audio generation and restoration has substantially improved performance across heterogeneous conditioning regimes, including text-conditioned audio generation and audio-conditioned super-resolution.…

The generation of emotional talking faces from a single portrait image remains a significant challenge. The simultaneous achievement of expressive emotional talking and accurate lip-sync is particularly difficult, as expressiveness is often…

Diffusion generative models transform noise into data by inverting a process that progressively adds noise to data samples. Inspired by concepts from the renormalization group in physics, which analyzes systems across different scales, we…

Deep denoising models require extensive real-world training data, which is challenging to acquire. Current noise synthesis techniques struggle to accurately model complex noise distributions. We propose a novel Realistic Noise Synthesis…

Sampling from diffusion models can be treated as solving the corresponding ordinary differential equations (ODEs), with the aim of obtaining an accurate solution with as few number of function evaluations (NFE) as possible. Recently,…

Although EDM aims to unify the design space of diffusion models, its reliance on fixed Gaussian noise prevents it from explaining emerging flow-based methods that diffuse arbitrary noise. Moreover, our study reveals that EDM's forcible…

The goal of this paper is to generate realistic audio with a lightweight and fast diffusion-based vocoder, named FreGrad. Our framework consists of the following three key components: (1) We employ discrete wavelet transform that decomposes…

Singing voice synthesis (SVS) aims to generate expressive and high-quality vocals from musical scores, requiring precise modeling of pitch, duration, and articulation. While diffusion-based models have achieved remarkable success in image…

Diffusion-based generative models learn to iteratively transfer unstructured noise to a complex target distribution as opposed to Generative Adversarial Networks (GANs) or the decoder of Variational Autoencoders (VAEs) which produce samples…

Diffusion (score-based) generative models have been widely used for modeling various types of complex data, including images, audios, and point clouds. Recently, the deep connection between forward-backward stochastic differential equations…

The introduction of audio latent diffusion models possessing the ability to generate realistic sound clips on demand from a text description has the potential to revolutionize how we work with audio. In this work, we make an initial attempt…

While Diffusion Generative Models have achieved great success on image generation tasks, how to efficiently and effectively incorporate them into speech generation especially translation tasks remains a non-trivial problem. Specifically,…

Modern text-to-speech synthesis pipelines typically involve multiple processing stages, each of which is designed or learnt independently from the rest. In this work, we take on the challenging task of learning to synthesise speech from…

Audio super-resolution is challenging owing to its ill-posed nature. Recently, the application of diffusion models in audio super-resolution has shown promising results in alleviating this challenge. However, diffusion-based models have…

Image synthesis is expected to provide value for the translation of machine learning methods into clinical practice. Fundamental problems like model robustness, domain transfer, causal modelling, and operator training become approachable…

Recent diffusion models have achieved promising performances in audio-denoising tasks. The unique property of the reverse process could recover clean signals. However, the distribution of real-world noises does not comply with a single…