The Noise Reduction of Speech Signals Based on Radial Basis Function Networks

• Main Authors: Chia-Hua Wu, 吳家華
• Other Authors: Te-Jen Su
• Format: Others
• Language: zh-TW
• Published: 2014
• Online Access: http://ndltd.ncl.edu.tw/handle/nbqmcz

碩士 === 國立高雄應用科技大學 === 電子工程系碩士班 === 103 === The voice in the transmission of signals is often accompanied with a lot of unnecessary disturbing noise. Usually, sound-absorbing cotton or directional microphones are applied on the hardware to suppress the background noise caused by the unwanted signals, such as sound of wind and human voice. In addition, the channel effects, like the microphone channel effect and the telephone channel effect, are generated among various voice-processing systems when voice signals are transferred. Thus, a variety of noise patterns are formed as a result these channel effects. The purpose of this thesis is to strengthen voice systems by using MATLAB to read the speech, adding the Additive White Gaussian Noise (AWGN), reading the speech in an open environment and finally applying the Radial Basis Function Networks (RBFN) in artificial neural networks to remove the noise.