“Adaptive training of hidden Markov models for stylistic walk synthesis” by Tilmanne and Dutoit

In this extended abstract, we present the use of Hidden Markov Models (HMMs) in order to synthesize walk sequences with a given style using a small amount of training data from the target style. As a first step, a general model of walk is built. Starting from that model, an adaptive training enables to adapt our model to any particular style using only a small amount of training data. This technique, which was originally developed for speaker adaptation in speech synthesis [Zen et al. 2007], enables to reduce the main problem of machine learning techniques which is the large amount of data needed to train each new model, and to adapt models to the exaggerated style variations of our database that were far from an average walk.

1. Zen, H., Nose, T., Yamagishi, J., Sako, S., Black, T. M. A. W., and Tokuda, K. 2007. The HMM-based Speech Synthesis System (HTS) Version 2.0. In Proceedings of the 6th ISCA Workshop on Speech Synthesis, Bonn, Germany, 294–299.