Title :
Study on speaker recognition under noise environments based on PCANN
Author :
Bao, Yong-Qiang ; Zhao, Li ; Cai-Rong, Z.W.
Author_Institution :
Dept. of Radio Eng., Southeast Univ., Nanjing, China
Abstract :
For unsatisfactory speaker recognition performance in noisy environments, this paper presents an algorithm to improve the noise robustness of the speaker recognition system based on PCANN. The modified spectral subtraction algorithm is presented to reduce the effect of the additive noise according to the properties of noise. Some experiments were conducted to demonstrate the efficiency of the new algorithm.
Keywords :
AWGN; neural nets; principal component analysis; speaker recognition; PCANN; additive noise; noise environment; principal component analysis neural network; speaker recognition system; spectral subtraction algorithm; Additive noise; Noise reduction; Noise robustness; Performance analysis; Phase noise; Signal processing algorithms; Speaker recognition; Speech enhancement; Speech recognition; Working environment noise;
Conference_Titel :
Machine Learning and Cybernetics, 2004. Proceedings of 2004 International Conference on
Print_ISBN :
0-7803-8403-2
DOI :
10.1109/ICMLC.2004.1380481
