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 …

Speech is the fundamental mode of human communication, and its synthesis has long been
a core priority in human–computer interaction research. In recent years, machines have …

Self-supervised learning in speech involves training a speech representation network on a
large-scale unannotated speech corpus, and then applying the learned representations to …

An Introduction to Variational Autoencoders Page 1 An Introduction to Variational Autoencoders
Page 2 Other titles in Foundations and Trends R in Machine Learning Computational Optimal …

Despite the progress in voice conversion, many-to-many voice conversion trained on non-
parallel data, as well as zero-shot voice conversion, remains under-explored. Deep style …

In this paper, we first provide a review of the state-of-the-art emotional voice conversion
research, and the existing emotional speech databases. We then motivate the development …

Automatic speaker verification (ASV) is one of the most natural and convenient means of
biometric person recognition. Unfortunately, just like all other biometric systems, ASV is …

This paper proposes a method that allows non-parallel many-to-many voice conversion (VC)
by using a variant of a generative adversarial network (GAN) called StarGAN. Our method …

We propose a non-parallel voice-conversion (VC) method that can learn a map** from
source to target speech without relying on parallel data. The proposed method is particularly …

Speech information can be roughly decomposed into four components: language content,
timbre, pitch, and rhythm. Obtaining disentangled representations of these components is …