Achieving High-Accuracy Text-to-Speech with Machine Learning

In 1987, Sejnowski and Rosenberg developed their famous NETtalk system for English textto -speech. This chapter describes a machine learning approach to text-to-speech that builds upon and extends the initial NETtalk work. Among the many extensions to the NETtalk system were the following: a different learning algorithm, a wider input "window", error-correcting output coding, a right-to-left scan of the word to be pronounced (with the results of each decision influencing subsequent decisions), and the addition of several useful input features. These changes yielded a system that performs much better than the original NETtalk system. After training on 19,002 words, the system achieves 93.7% correct pronunciation of individual phonemes and 64.8% correct pronunciation of whole words (where the pronunciation must exactly match the dictionary pronunciation to be correct). Based on the judgements of three human participants in a blind assessment study, our system was estimated to have a seri..