Related papers: ArrayDPS-Refine: Generative Refinement of Discrimi…

Over the recent years, various deep learning-based methods were proposed for extracting a fixed-dimensional embedding vector from speech signals. Although the deep learning-based embedding extraction methods have shown good performance in…

Speech enhancement and speech separation are two related tasks, whose purpose is to extract either one or more target speech signals, respectively, from a mixture of sounds generated by several sources. Traditionally, these tasks have been…

In the visual generative area, discrete diffusion models are gaining traction for their efficiency and compatibility. However, pioneered attempts still fall behind their continuous counterparts, which we attribute to noise (absorbing state)…

This paper describes several improvements to a new method for signal decomposition that we recently formulated under the name of Differentiable Dictionary Search (DDS). The fundamental idea of DDS is to exploit a class of powerful deep…

Despite consistent advancement in powerful deep learning techniques in recent years, large amounts of training data are still necessary for the models to avoid overfitting. Synthetic datasets using generative adversarial networks (GAN) have…

A promising approach for speech dereverberation is based on supervised learning, where a deep neural network (DNN) is trained to predict the direct sound from noisy-reverberant speech. This data-driven approach is based on leveraging prior…

Speech enhancement techniques based on deep learning have brought significant improvement on speech quality and intelligibility. Nevertheless, a large gain in speech quality measured by objective metrics, such as perceptual evaluation of…

For multi-channel speech recognition, speech enhancement techniques such as denoising or dereverberation are conventionally applied as a front-end processor. Deep learning-based front-ends using such techniques require aligned clean and…

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…

Diffusion models have gained attention in speech enhancement tasks, providing an alternative to conventional discriminative methods. However, research on target speech extraction under multi-speaker noisy conditions remains relatively…

Speech enhancement is designed to enhance the intelligibility and quality of speech across diverse noise conditions. Recently, diffusion model has gained lots of attention in speech enhancement area, achieving competitive results. Current…

A promising approach for multi-microphone speech separation involves two deep neural networks (DNN), where the predicted target speech from the first DNN is used to compute signal statistics for time-invariant minimum variance…

The proposed method, Discriminator Guidance, aims to improve sample generation of pre-trained diffusion models. The approach introduces a discriminator that gives explicit supervision to a denoising sample path whether it is realistic or…

Diffusion models have achieved remarkable success in generating high-resolution, realistic images across diverse natural distributions. However, their performance heavily relies on high-quality training data, making it challenging to learn…

Eliminating the negative effect of non-stationary environmental noise is a long-standing research topic for automatic speech recognition that stills remains an important challenge. Data-driven supervised approaches, including ones based on…

This study proposes a multi-microphone complex spectral mapping approach for speech dereverberation on a fixed array geometry. In the proposed approach, a deep neural network (DNN) is trained to predict the real and imaginary (RI)…

Traditional speech enhancement methods often oversimplify the task of restoration by focusing on a single type of distortion. Generative models that handle multiple distortions frequently struggle with phone reconstruction and…

Most soundfield synthesis approaches deal with extensive and regular loudspeaker arrays, which are often not suitable for home audio systems, due to physical space constraints. In this article we propose a technique for soundfield synthesis…

Contemporary speech enhancement predominantly relies on audio transforms that are trained to reconstruct a clean speech waveform. The development of high-performing neural network sound recognition systems has raised the possibility of…

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…