Text-To-Speech Conversion with Neural Networks: A Recurrent TDNN Approach
Neural and Evolutionary Computing
2016-08-31 v1 Human-Computer Interaction
Abstract
This paper describes the design of a neural network that performs the phonetic-to-acoustic mapping in a speech synthesis system. The use of a time-domain neural network architecture limits discontinuities that occur at phone boundaries. Recurrent data input also helps smooth the output parameter tracks. Independent testing has demonstrated that the voice quality produced by this system compares favorably with speech from existing commercial text-to-speech systems.
Cite
@article{arxiv.cs/9811032,
title = {Text-To-Speech Conversion with Neural Networks: A Recurrent TDNN Approach},
author = {Orhan Karaali and Gerald Corrigan and Ira Gerson and Noel Massey},
journal= {arXiv preprint arXiv:cs/9811032},
year = {2016}
}
Comments
4 pages, PostScript