Abstract: The improved wavelet denoising method is used to process the noisy speech at the front end, and the wavelet coefficients are weighted before wavelet reconstruction according to the characteristics of speaker recognition; the GMM recognition algorithm is used in the recognition process. The experimental results show that the proposed method has obvious advantages in speaker recognition with noisy speech compared with speaker recognition that purely uses MFCC as recognition features. This method has a good guiding role in real-time speaker recognition.
You Might Like
Recommended ContentMore
Open source project More
Popular Components
Searched by Users
Just Take a LookMore
Trending Downloads
Trending ArticlesMore