4th International Conference on Spoken Language Processing

Philadelphia, PA, USA
October 3-6, 1996

High-quality Prosodic Modification of Speech Signals

Beat Pfister

Computer Engineering and Networks Laboratory (TIK), Speech Processing Group, ETH Zürich, Switzerland

The aim of this work was to develop a procedure that allows prosodic modifications of speech signals without impairing the quality. The developed procedure is based on the Fourier analysis/synthesis technique with several improvements on the analysis side, such as the analysis of signals with rapidly changing F0 and the analysis of weak spectral components. Also for the modification of the short-time spectrum and for the reconstruction of the speech signal some new methods have been introduced. The most important one, in terms of speech quality, is the way of phase compensation that limits the absolute time shift to half the pitch period. The developed procedure is used in our high-quality text-to-speech synthesis system that is based on concatenation of prosodically modified diphones.

Full Paper   Sound Example

Bibliographic reference.  Pfister, Beat (1996): "High-quality prosodic modification of speech signals", In ICSLP-1996, 2446-2449.