Catalogue of Artificial Intelligence Techniques
Author(s): Andrej Ljolje
There are three main algorithms used for performing pitch extraction for speech synthesis and recognition: the Gold-Rabiner parallel processing method with voiced-unvoiced decision, the Dubnowski autocorrelation method and the Harmonic-sieve pitch extraction method.
- Duifhuis, H., Willems, L.F. and Sluyter, R.J., Measurement of pitch in speech: an implementation of Goldstein's theory of pitch perception
JASA 71 (1982) no.6, 1568--1580.