Categories | Inventors

Full Text To Speech with OGIResLPC


OHSU # 0631

Technology Overview:

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.

Related Technologies:

  • OHSU # 1364 — Mexican Spanish male diphone voice
  • OHSU # 1363 — American English female diphone voice (TL)
  • OHSU # 1365 — Mexican Spanish female diphone voice
  • OHSU # 1362 — American English female diphone voice (AS)
  • OHSU # 1361 — American English male speaker diphone voice
  • OHSU # 1360 — German male speaker diphone voice
  • OHSU # 1359 — German female speaker diphone voice


For more information, contact:

Trina Voss
Technology Development Manager