Gestures that accompany speech are an essential part of natural and efficient embodied
human communication. The automatic generation of such co‐speech gestures is a long …

Generating versatile and appropriate synthetic speech requires control over the output
expression separate from the spoken text. Important non-textual speech variation is seldom …

Deep neural networks (DNNs) have recently been the focus of much text-to-speech research
as a replacement for decision trees and hidden Markov models (HMMs) in statistical …

Neural sequence-to-sequence TTS has achieved significantly better output quality than
statistical speech synthesis using HMMs. However, neural TTS is generally not probabilistic …

Neural HMMs are a type of neural transducer recently proposed for sequence-to-sequence
modelling in text-to-speech. They combine the best features of classic statistical speech …

Vocoding of speech is a standard part of statistical parametric speech synthesis systems. It
imposes an upper bound of the naturalness that can possibly be achieved. Hybrid systems …

Text does not fully specify the spoken form, so text-to-speech models must be able to learn
from speech data that vary in ways not explained by the corresponding text. One way to …

Neural-network-based generative models, such as mixture density networks, are potential
solutions for speech synthesis. In this paper we follow this path and propose a recurrent …

For building flexible and appealing high-quality speech synthesisers, it is desirable to be
able to accommodate and reproduce fine variations in vocal expression present in natural …

Accurate modelling and prediction of speech-sound durations is an important component in
generating more natural synthetic speech. Deep neural networks (DNNs) offer a powerful …