Full Text To Speech with OGIResLPC

Case ID:
0631
Web Published:
6/24/2009
Description:

Technology Overview

This is a signal processing sub-system for the Festival open-source text-to-speech system. The task of the sub-system is to concatenate acoustic units, modify pitch and timing of the speech signal after concatenation. The sub-system is based on residual-excited linear prediction.

 

Recordings are analyzed via linear prediction, the reflection coefficients and residuals are stored, and, during pitch and timing modification, overlap-add algorithms are applied to the residuals signal. This system produces higher quality speech than systems in which the excitation is provided by pulses or white noise.

Patent Information:
Category(s):
Speech & Language
For Information, Contact:
Trina Voss
Technology Development Manager
Oregon Health & Science University
4-8200
vosst@ohsu.edu
Inventors:
Michael Macon
Keywords:
Education & Training
Education & Training - Speech & Language
Software
© 2018. All Rights Reserved. Powered by Inteum