Intonation modelling using a muscle model and perceptually weighted matching pursuit

Abstract

We propose a physiologically based intonation model using perceptual relevance. Motivated by speech synthesis from a speech-to-speech translation (S2ST) point of view, we aim at a language independent way of modelling intonation. The model presented in this paper can be seen as a generalisation of the command response (CR) model, albeit with the same modelling power. It is an additive model which decomposes intonation contours into a sum of critically damped system impulse responses. To decompose the intonation contour, we use a weighted correlation based atom decomposition algorithm (WCAD) built around a matching pursuit framework. The algorithm allows for an arbitrary precision to be reached using an iterative procedure that adds more elementary atoms to the model. Experiments are presented demonstrating that this generalised CR (GCR) model is able to model intonation as would be expected. Experiments also show that the model produces a similar number of parameters or elements as the CR model. We conclude that the GCR model is appropriate as an engineering solution for modelling prosody, and hope that it is a contribution to a deeper scientific understanding of the neurobiological process of intonation.

A Bayesian Approach to Recurrence in Neural Networks

“…This can be explained by our second hypothesis. Physiological filters are known to have asymmetric impulse responses [36]. This is one explanation for the large improvement arising from doubling up the Uni-GRU to explicitly modelling the backward recursion.…”

Multi-Spectral Widefield Microscopy of the Beating Heart Through Post-Acquisition Synchronization and Unmixing

“…This can be explained by our second hypothesis. Physiological filters are known to have asymmetric impulse responses [Honnet et al, 2018]. This is one explanation for the large improvement arising from doubling up the Uni-GRU to explicitly modelling the backward recursion.…”