The Simple4All entry to the Blizzard Challenge 2014
Antti Suni, Tuomo Raitio, Dhananjaya Gowda, Reima Karhila, Matt Gibson, Oliver Watts · 2014
We describe the synthetic voices entered into the 2014 Bliz-zard Challenge by the SIMPLE4ALL consortium. The 2014 Blizzard Challenge presents an opportunity to test and bench-mark some of the tools we have been developing to address the problem of how to produce systems in arbitrary new languages with minimal annotated data and language-specific expertise on the part of the system builders. We here explain how our tools were used to address these problems on the different tasks of the challenge, and provide some discussion of the evaluation results. Several additions to the system used to build voices for the previous Challenge are described: naive alphabetisation, unsupervised syllabification, and glottal flow pulse prediction using deep neural networks. Index Terms: statistical parametric speech synthesis, unsu-pervised learning, vector space model, glottal inverse filtering, deep neural network, glottal flow pulse library 1.