Related papers: Speech Enhancement and Dereverberation with Diffus…

Acoustic echo and background noise pose challenges on speech enhancement in hands-free systems and speakerphones. Discriminatively trained end-to-end methods represent a powerful solution for joint acoustic echo control (AEC) and denoising.…

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…

Diffusion model-based speech enhancement has received increased attention since it can generate very natural enhanced signals and generalizes well to unseen conditions. Diffusion models have been explored for several sub-tasks of speech…

Deep neural network based speech enhancement technique focuses on learning a noisy-to-clean transformation supervised by paired training data. However, the task-specific evaluation metric (e.g., PESQ) is usually non-differentiable and can…

Diffusion models have emerged as a dominant framework for generative modeling, but their mathematical foundations are often presented separately through diffusion probabilistic models, score-based modeling, stochastic differential…

We enhance the vanilla adversarial training method for unsupervised Automatic Speech Recognition (ASR) by a diffusion-GAN. Our model (1) injects instance noises of various intensities to the generator's output and unlabeled reference text…

In this paper, we propose a model to perform speech dereverberation by estimating its spectral magnitude from the reverberant counterpart. Our models are capable of extracting features that take into account both short and long-term…

This paper proposes a speech enhancement method which exploits the high potential of residual connections in a Wide Residual Network architecture. This is supported on single dimensional convolutions computed alongside the time domain,…

Generative models have shown robust performance on speech enhancement and restoration tasks, but most prior approaches operate offline with high latency, making them unsuitable for streaming applications. In this work, we investigate the…

Diffusion-based speech enhancement (SE) achieves natural-sounding speech and strong generalization, yet suffers from key limitations like generative artifacts and high inference latency. In this work, we systematically study artifact…

Enhancing speech signal quality in adverse acoustic environments is a persistent challenge in speech processing. Existing deep learning based enhancement methods often struggle to effectively remove background noise and reverberation in…

Generative speech enhancement methods based on generative adversarial networks (GANs) and diffusion models have shown promising results in various speech enhancement tasks. However, their performance in very low signal-to-noise ratio (SNR)…

The diffusion model is capable of generating high-quality data through a probabilistic approach. However, it suffers from the drawback of slow generation speed due to the requirement of a large number of time steps. To address this…

Diffusion models have shown exceptional scaling properties in the image synthesis domain, and initial attempts have shown similar benefits for applying diffusion to unconditional text synthesis. Denoising diffusion models attempt to…

Extracting individual elements from music mixtures is a valuable tool for music production and practice. While neural networks optimized to mask or transform mixture spectrograms into the individual source(s) have been the leading approach,…

The speech enhancement task usually consists of removing additive noise or reverberation that partially mask spoken utterances, affecting their intelligibility. However, little attention is drawn to other, perhaps more aggressive signal…

Diffusion-based generative models have greatly impacted the speech processing field in recent years, exhibiting high speech naturalness and spawning a new research direction. Their application in real-time communication is, however, still…

The denoising process of diffusion models can be interpreted as an approximate projection of noisy samples onto the data manifold. Moreover, the noise level in these samples approximates their distance to the underlying manifold. Building…

Score-based diffusion models have significantly advanced generative deep learning for image processing. Measurement conditioned models have also been applied to inverse problems such as CT reconstruction. However, the conventional approach,…

Separating the individual elements in a musical mixture is an essential process for music analysis and practice. While this is generally addressed using neural networks optimized to mask or transform the time-frequency representation of a…