Adaptive Filtering and Voice Compression Using Neural Networks

Voice data compression is about a process which reduces the data rate or file size of digital audio signals. This process reduces the dynamic range without changing the amount of digital data of audio signals. Voice compression is one of the leading vicinity of digital signal processing that spotlight on dipping the bit rate of speech signals for transmission and storage devoid of considerable loss of quality. This paper attempts to present an adaptive filtering technique for the removal of useless noise from the audio signals. After the noise removal has been done, the filtered audio signal is taken as the input to the neural network. Finally, the back propagation algorithm is applied for the compression of the audio signals.