Further reduced form of wavelet feature for text independent speaker recognition

摘要

A text independent speaker recognition system based on wavelet transform derived from fuzzy c-means clustering is proposed. The fuzzy e-means clustering is applied to the speaker data compression in spectrum domain. A set of experiments are conducted, which gives a 95% recognition rate for 100 Mandarin speakers. (C) 2004 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.