Noise Reduction Methodology for Audio and Speech Signal

The speech signal is plays an important role in multimedia system. In this paper, Main objective is to reduce noise from audio signal which is heavily dependent on the specific context and application. Noise acts as the disturbance in any form of communication which degrades the quality of the information signal . Noise reduction is the process of removing background noise from speech signal. Many methods have been widely used to eliminate noise from speech signal like thresholding , discrete wavelet transform. The audio signal corrupted with white Gaussian noise which is especially hard to remove because it is located in all frequency, where Gaussion noise is inserted into an audio signal, this noise is used at different SNR levels .Discrete Wavelet technique is effectively reduces the unwanted higher or lower order frequency components in a speech signal. Soft and hard thresholding are used for denoising the signal. Soft thresholding method performs better than hard thresholding at all input SNR levels. The different wavelet types such as coiflet, daubechies, symlet are used to measure the performance. Wavelet are localized both in time and frequency. It is implemented by using different parameters such as SNR, Elapsed time.