Abstract
This letter proposes an effective and robust speech feature extraction method based on statistical analysis of Pitch Frequency Distributions (PFD) for speaker identification. Compared with the conventional cepstrum, PFD is relatively insensitive to Additive White Gaussian Noise (AWGN), but it does not show good performance for speaker identification, even if under clean environments. To compensate this shortcoming, PFD and conventional cepstrum are combined to make the ultimate decision, instead of simple taking one kind of features into account Experimental results indicate that the hybrid approach can give outstanding improvement for text-independent speaker identification under noisy environments corrupted by AWGN.
References
K. T. Assaleh, R. J. Mammone, New LP-derived features for speaker identification, IEEE Trans. on Speech and Audio Processing, 2(1994)4, 630–638.
Yu-Hung Kao, Robustness study of free-text speaker identification and verification, Ph.D. dissertation, Univ. Of Maryland, Dec. 1992.
S. Ahmadi, A. S. Spanias, Cepstrum-based pitch detection using a new statistical V/UV classification algorithm, IEEE Trans. on Speech and Audio Processing, 7(1999)3, 333–338.
D. A. Reynolds, R. C. Rose, Robust text-independent speaker identification using Gaussian mixture speaker models, IEEE Trans. on Speech and Audio Processing, 3(1995)1, 72–83.
R. J. Mammone, X. Zhang, et al., Robust speaker recognition: A feature-based approach, IEEE Signal Processing Magazine, 13(1996)5, 58–71.
Author information
Authors and Affiliations
Additional information
Communication author: Zhang Linghua, born in 1964, female, associate professor. Department of Information Engineering, Nanjing University of Posts & Telecommunications, Nanjing 210003, China.
About this article
Cite this article
Zhang, L., Zheng, B. & Yang, Z. Statistical feature of pitch frequency distributions for robust speaker identification. J. of Electron.(China) 22, 437–442 (2005). https://doi.org/10.1007/BF02687916
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02687916