Abstract
Speech enhancement has a considerable attention in the use of speech transmission through the communication channel, speaker identification, speech-based biometric system, video conference, hearing aids, mobile phones, voice conversion, microphones, and so on. Consideration to the background noise processing is required in order to design a successful speech enhancement system. In this chapter, a proposed approach of speech enhancement based on SBWT and minimum mean square error (MMSE) estimate of spectral amplitude is detailed. It consists at the first step in applying the SBWT to the noisy speech signal for obtaining eight noisy stationary bionic wavelet coefficients. Each of them is denoised applying a denoising technique based on MMSE estimate of spectral amplitude. Finally, the inverse of SBWT (SBWT −1) is applied to the denoised stationary bionic wavelet coefficients for obtaining the enhanced speech signal. The performance of this approach is proved from the results obtained from the computation of the signal-to-noise ratio (SNR), the segmental SNR (SSNR), and the perceptual evaluation of speech quality (PESQ).KeywordsSpeech enhancement SBWT MMSE Spectral amplitude
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call