摘要 |
A compressing a voice signal by the steps of (a) digitizing an input signal that includes a voice signal, the input signal including a coherent noise component; and (b) compressing the digitized voice signal with a synchronized overlap add processor (20). So as to prevent the synchronized overlap add processor from locking to the coherent noise component, the step of compressing includes an initial step of applying the digitized input signal to a linear predictor (16), the linear predictor having time constants selected for attenuating the coherent noise component of the input signal. The residual signal output of the linear predictor includes the voice signal, and an uncorrelated noise component if one is present in the input signal. The operation of the synchronized overlap add processor also functions to attenuate the incoherent noise component. Further compression of the compressed voice signal is accomplished by Huffman coding, arithmetic coding, or transform coding so as to provide a greatly compressed voice signal that, when subsequently expanded, is found to exhibit excellent voice quality.
|