Quantization of transmission parameters in stereo linear predictive systems

Linear prediction (LP) is a widely used technique in single-channel speech coding. LP can also be applied to stereo (or multi-channel) audio coding, but it requires a scheme for quantization and efficient transmission of stereo-LP parameters. We propose to transmit the (forward) normalized reflection matrices together with the zero-lag correlation matrix. Furthermore, we select a parameterization for the matrices and a quantization strategy per parameter. The parameterization for the normalized reflection matrices is a variant of the singular value decomposition (SVD). The proposed quantization scheme is evaluated for first-order stereo-LP systems. As criterion, we use a spectral distortion (SD) measure based on the norm of the transfer matrix of the synthesis filter. Simulations show that the distortions can easily be controlled as a function of bit rate