相关论文: Can We Trust Deep Speech Prior?

The variational autoencoder (VAE; Kingma, Welling (2014)) is a recently proposed generative model pairing a top-down generative network with a bottom-up recognition network which approximates posterior inference. It typically makes strong…

Real-time speech enhancement (SE) is essential to online speech communication. Causal SE models use only the previous context while predicting future information, such as phoneme continuation, may help performing causal SE. The phonetic…

Speech enhancement is a critical component of many user-oriented audio applications, yet current systems still suffer from distorted and unnatural outputs. While generative models have shown strong potential in speech synthesis, they are…

Convolutional neural networks contain strong priors for generating natural looking images [1]. These priors enable image denoising, super resolution, and inpainting in an unsupervised manner. Previous attempts to demonstrate similar ideas…

Spatial filters can exploit deep-learning-based speech enhancement models to increase their reliability in scenarios with multiple speech sources scenarios. To further improve speech quality, it is common to perform postfiltering on the…

Variational Autoencoders (VAE) are probabilistic deep generative models underpinned by elegant theory, stable training processes, and meaningful manifold representations. However, they produce blurry images due to a lack of explicit…

Deep learning-based models have greatly advanced the performance of speech enhancement (SE) systems. However, two problems remain unsolved, which are closely related to model generalizability to noisy conditions: (1) mismatched noisy…

Deep generative models have achieved great success in unsupervised learning with the ability to capture complex nonlinear relationships between latent generating factors and observations. Among them, a factorized hierarchical variational…

Despite significant progress made in the last decade, deep neural network (DNN) based speech enhancement (SE) still faces the challenge of notable degradation in the quality of recovered speech under low signal-to-noise ratio (SNR)…

Speech enhancement (SE) aims to reduce noise in speech signals. Most SE techniques focus only on addressing audio information. In this work, inspired by multimodal learning, which utilizes data from different modalities, and the recent…

Speech enhancement (SE) aims to reduce noise in speech signals. Most SE techniques focus only on addressing audio information. In this work, inspired by multimodal learning, which utilizes data from different modalities, and the recent…

Monaural speech enhancement has made dramatic advances since the introduction of deep learning a few years ago. Although enhanced speech has been demonstrated to have better intelligibility and quality for human listeners, feeding it…

In this study we present a mixture of deep experts (MoDE) neural-network architecture for single microphone speech enhancement. Our architecture comprises a set of deep neural networks (DNNs), each of which is an 'expert' in a different…

The amount of articulatory data available for training deep learning models is much less compared to acoustic speech data. In order to improve articulatory-to-acoustic synthesis performance in these low-resource settings, we propose a…

Both reverberation and additive noises degrade the speech quality and intelligibility. Weighted prediction error (WPE) method performs well on the dereverberation but with limitations. First, WPE doesn't consider the influence of the…

Most existing word embedding methods can be categorized into Neural Embedding Models and Matrix Factorization (MF)-based methods. However some models are opaque to probabilistic interpretation, and MF-based methods, typically solved using…

Deep learning has revolutionized the last decade, being at the forefront of extraordinary advances in a wide range of tasks including computer vision, natural language processing, and reinforcement learning, to name but a few. However, it…

Speech emotion recognition (SER) has long benefited from the adoption of deep learning methodologies. Deeper models -- with more layers and more trainable parameters -- are generally perceived as being `better' by the SER community. This…

Semi-supervised learning is sought for leveraging the unlabelled data when labelled data is difficult or expensive to acquire. Deep generative models (e.g., Variational Autoencoder (VAE)) and semisupervised Generative Adversarial Networks…

Deep generative models applied to audio have improved by a large margin the state-of-the-art in many speech and music related tasks. However, as raw waveform modelling remains an inherently difficult task, audio generative models are either…