Perceptually-based coding for root LPC synthesis

Efficient automatic coding of narrow-band speech requires an analytical measure of distance that corresponds in some sense to our aural perception. Such measures as mean-square spectral deviation are useful perceptual correlates in extreme cases only; counter-examples abound. An alternative metric can be formulated from experimentally determined limens of formant spectral deviation. These considerations have led to the development of a formant-based ordering and quantization scheme for the quadratic coefficients derived from root extraction of the LPC polynomial. The resultant parameters are used to emulate the performance of a newly designed IC speech synthesizer. The synthetic speech requires 1000 to 2000 bits per second of parameter storage. Informal listening tests with this synthesis indicate little degradation over the unquantized speech.