Speaker Recognition from Noisy Spoken Sentences
Fatima Faek, Abdulbasit K. Al‐Talabani · International Journal of Computer Applications · 2013
In this paper a text independent speaker recognizer from controlled noisy speech signals has been investigated.A recorded data is used for 20 Kurdish speakers (10 males, and 10 females) .The feature used in this work is the MFCC, and k-NN is used as a classifier.The recognition performance from the noisy speech signals has been improved by a denoising technique using wavelet transform.The result show that the de-noising technique could improve the performance of speaker recognizer by about 36%.