Performance evaluation of a wavelet-based pitch detection scheme

Abstract

Performance evaluation, in a complete speech analysis-synthesis system, has been carried out for a wavelet-based pitch detection scheme that has been reported earlier. Speech quality, time for computation and memory consumption (for real-time implementation) are the parameters that have been considered while comparing this system with analysis-synthesis systems that use pitch detection based on autocorrelation and cepstral analysis. Results for different speech signals show that autocorrelation-based pitch detection scheme is the best in terms of speech quality and memory consumption while wavelet-based pitch detection stands in between the other two methods.