Speech quality evaluation for different pitch detection algorithms in LPC speech analysis–synthesis system

Abstract

In this paper, the performance comparison of three pitch detection algorithms (PDAs) has been presented by implementing them in a LPC based speech analysis-synthesis system. The PDAs considered for comparison is based on three paradigms. The paradigms are weighted autocorrelation function (WACF), Empirical Mode Decomposition based autocorrelation function (EMD-ACF) and Empirical Mode Decomposition based average magnitude difference function (EMD-AMDF). Speech quality measurement is an important and essential task to ensure and maintain the quality of services for speech processing applications like modern telecommunication. Hence, the performance of these methods has been compared through the output speech quality using objective (perceptual evaluation of speech quality test) and subjective quality assessment (Mean Opinion Score test, diagnostic rhyme test and synthesized speech waveforms). The results show that the speech quality for the EMD-ACF and EMD-AMDF based PDA’s are better than that for WACF based PDA. The works presented in this paper is beneficial to telecommunication and speech recognition research group.