Related papers: MeanSE: Efficient Generative Speech Enhancement wi…

Popular neural network-based speech enhancement systems operate on the magnitude spectrogram and ignore the phase mismatch between the noisy and clean speech signals. Conditional generative adversarial networks (cGANs) show promise in…

Generative speech enhancement has recently shown promising advancements in improving speech quality in noisy environments. Multiple diffusion-based frameworks exist, each employing distinct training objectives and learning techniques. This…

Audio-visual speech enhancement (AV-SE) methods utilize auxiliary visual cues to enhance speakers' voices. Therefore, technically they should be able to outperform the audio-only speech enhancement (SE) methods. However, there are few works…

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…

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…

Real-world speech recordings suffer from degradations such as background noise and reverberation. Speech enhancement aims to mitigate these issues by generating clean high-fidelity signals. While recent generative approaches for speech…

The intelligibility of speech severely degrades in the presence of environmental noise and reverberation. In this paper, we propose a novel deep learning based system for modifying the speech signal to increase its intelligibility under the…

Single-channel speech enhancement with deep neural networks (DNNs) has shown promising performance and is thus intensively being studied. In this paper, instead of applying the mean squared error (MSE) as the loss function during DNN…

Building a single universal speech enhancement (SE) system that can handle arbitrary input is a demanded but underexplored research topic. Towards this ultimate goal, one direction is to build a single model that handles diverse audio…

We introduce AnyEnhance, a unified generative model for voice enhancement that processes both speech and singing voices. Based on a masked generative model, AnyEnhance is capable of handling both speech and singing voices, supporting a wide…

Statistical signal processing based speech enhancement methods adopt expert knowledge to design the statistical models and linear filters, which is complementary to the deep neural network (DNN) based methods which are data-driven. In this…

Speech enhancement (SE) is the foundational task of enhancing the clarity and quality of speech in the presence of non-stationary additive noise. While deterministic deep learning models have been commonly employed for SE, recent research…

High quality speech capture has been widely studied for both voice communication and human computer interface reasons. To improve the capture performance, we can often find multi-microphone speech enhancement techniques deployed on various…

Existing deep learning based speech enhancement mainly employ a data-driven approach, which leverage large amounts of data with a variety of noise types to achieve noise removal from noisy signal. However, the high dependence on the data…

A large part of the expressive speech synthesis literature focuses on learning prosodic representations of the speech signal which are then modeled by a prior distribution during inference. In this paper, we compare different prior…

Self-Supervised Learning (SSL) models have demonstrated exceptional performance in various speech tasks, particularly in low-resource and multilingual domains. Recent works show that fusing diverse SSL models could achieve superior…

Most sentence embedding techniques heavily rely on expensive human-annotated sentence pairs as the supervised signals. Despite the use of large-scale unlabeled data, the performance of unsupervised methods typically lags far behind that of…

Generative adversarial networks (GAN) have recently been shown to be efficient for speech enhancement. However, most, if not all, existing speech enhancement GANs (SEGAN) make use of a single generator to perform one-stage enhancement…

Flow matching has emerged as a powerful generative framework, with recent few-step methods achieving remarkable inference acceleration. However, we identify a critical yet overlooked limitation: these models suffer from severe diversity…

In this work, we propose the Generative Latent Flow (GLF), an algorithm for generative modeling of the data distribution. GLF uses an Auto-encoder (AE) to learn latent representations of the data, and a normalizing flow to map the…