A noise-robust pitch synchronous feature extraction algorithm for speaker recognition systems

A noise-robust pitch synchronous feature extraction algorithm for speaker recognition systems is proposed in this paper. Since the pitch synchronous algorithms utilize pitch information, which is meaningful only for periodic segments, we propose a new scheme to deal with non-periodic ones such as unvoiced and noise-corrupted. The experimental results show that the proposed algorithm outperforms the conventional algorithm using fixed length of analysis window in actual identification tasks even in low SNR noisy environments.