Speaker identity is one of the important characteristics of human speech. In voice
conversion, we change the speaker identity from one to another, while kee** the linguistic …

New waves of consumer-centric applications, such as voice search and voice interaction
with mobile devices and home entertainment systems, increasingly require automatic …

This work proposes a fully convolutional neural network (CNN) for real-time speech
enhancement in the time domain. The proposed CNN is an encoder-decoder based …

Formulation of speech separation as a supervised learning problem has shown
considerable promise. In its simplest form, a supervised learning algorithm, typically a deep …

In this study, we explore long short-term memory recurrent neural networks (LSTM-RNNs)
for speech enhancement. First, a regression LSTM-RNN approach for a direct map** from …

Speech enhancement is challenging because of the diversity of background noise types.
Most of the existing methods are focused on modelling the speech rather than the noise. In …

Frequency-domain monaural speech enhancement has been extensively studied for over
60 years, and a great number of methods have been proposed and applied to many …

Source separation models that make use of nonnegativity in their parameters have been
gaining increasing popularity in the last few years, spawning a significant number of …

This paper presents a generative approach to speech enhancement based on a recurrent
variational autoencoder (RVAE). The deep generative speech model is trained using clean …

Dynamical variational autoencoders (DVAEs) are a class of deep generative models with
latent variables, dedicated to model time series of high-dimensional data. DVAEs can be …