Speech Synthesis with Neural Networks

TL;DR

This paper presents a neural network-based system for text-to-speech synthesis that improves memory efficiency and performance over traditional concatenation and rule-based methods.

Contribution

It introduces a neural network approach using TDNNs for phonetic-to-acoustic mapping and timing control, advancing speech synthesis technology.

Findings

Requires less memory than concatenation systems

Performs well in comparative tests with commercial systems

Demonstrates effective neural network application in speech synthesis

Abstract

Text-to-speech conversion has traditionally been performed either by concatenating short samples of speech or by using rule-based systems to convert a phonetic representation of speech into an acoustic representation, which is then converted into speech. This paper describes a system that uses a time-delay neural network (TDNN) to perform this phonetic-to-acoustic mapping, with another neural network to control the timing of the generated speech. The neural network system requires less memory than a concatenation system, and performed well in tests comparing it to commercial systems using other technologies.