On a pitch detection method using noise reduction

Abstract

It can be used to easily change or to maintain the naturalness and intelligibility of quality in speech synthesis and to eliminate the personality for speaker-independence in speech recognition. In this paper, we proposed a new pitch detection algorithm. And Kalman filters are implemented for filtering speech contaminated by additive white noise or colored noise and an iterative signal and parameter estimator which can be used for both noise type is presented. The performance was compared with LPC and Cepstrum, ACF. we have obtained the pitch information improved the accuracy of pitch detection and gross error rate is reduced in voice speech region and in transition region of changing the phoneme. Also the results indicate that the additive white noise Kalman filters provide an audible improvement in output speech quality, and an improved pitch detection. This paper clearly shows the feasibility of using the Kalman filter for noise reduction.