Related papers: FADI-AEC: Fast Score Based Diffusion Model Guided …

Existing diffusion-based purification methods aim to disrupt adversarial perturbations by introducing a certain amount of noise through a forward diffusion process, followed by a reverse process to recover clean examples. However, this…

We present Deep Compression Autoencoder (DC-AE), a new family of autoencoder models for accelerating high-resolution diffusion models. Existing autoencoder models have demonstrated impressive results at a moderate spatial compression ratio…

Being a form of biometric identification, the security of the speaker identification (SID) system is of utmost importance. To better understand the robustness of SID systems, we aim to perform more realistic attacks in SID, which are…

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…

We describe a joint acoustic echo cancellation (AEC) and blind source extraction (BSE) approach for multi-microphone acoustic frontends. The proposed algorithm blindly estimates AEC and beamforming filters by maximizing the statistical…

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,…

Diffusion-based image generation models excel at producing high-quality synthetic content, but suffer from slow and computationally expensive inference. Prior work has attempted to mitigate this by caching and reusing features within…

Although today's speech communication systems support various bandwidths from narrowband to super-wideband and beyond, state-of-the art DNN methods for acoustic echo cancellation (AEC) are lacking modularity and bandwidth scalability. Our…

Acoustic echo cancellation (AEC) is designed to remove echoes, reverberation, and unwanted added sounds from the microphone signal while maintaining the quality of the near-end speaker's speech. This paper proposes adaptive speech quality…

Deep clustering methods typically rely on a single, well-defined representation for clustering. In contrast, pretrained diffusion models provide abundant and diverse multi-scale representations across network layers and noise timesteps.…

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…

Removing background noise from speech audio has been the subject of considerable effort, especially in recent years due to the rise of virtual communication and amateur recordings. Yet background noise is not the only unpleasant disturbance…

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…

Autoregressive (AR) models with diffusion heads have recently achieved strong text-to-audio performance, yet their iterative decoding and multi-step sampling process introduce high-latency issues. To address this bottleneck, we propose a…

The emergence of diffusion models has significantly advanced generative AI, improving the quality, realism, and creativity of image and video generation. Among them, Stable Diffusion (StableDiff) stands out as a key model for text-to-image…

Surface electromyography (sEMG) recordings can be influenced by electrocardiogram (ECG) signals when the muscle being monitored is close to the heart. Several existing methods use signal-processing-based approaches, such as high-pass filter…

The strategy of combining diffusion-based generative models with classifiers continues to demonstrate state-of-the-art performance on adversarial robustness benchmarks. Known as adversarial purification, this exploits a diffusion model's…

Data-driven acoustic echo cancellation (AEC) methods, predominantly trained on synthetic or constrained real-world datasets, encounter performance declines in unseen echo scenarios, especially in real environments where echo paths are not…

Diffusion models are a new class of generative models that have shown outstanding performance in image generation literature. As a consequence, studies have attempted to apply diffusion models to other tasks, such as speech enhancement. A…

With recent advances of diffusion model, generative speech enhancement (SE) has attracted a surge of research interest due to its great potential for unseen testing noises. However, existing efforts mainly focus on inherent properties of…