Nonlinear predictive models computation in ADPCM schemes
This is an incremental improvement for speech coding systems, addressing robustness and generalization in training procedures.
The paper tackles the problem of improving nonlinear predictive models in ADPCM speech coding schemes, achieving up to 1.2dB gain in SEGSNR and more stable output quality by minimizing variance between frames.
Recently several papers have been published on nonlinear prediction applied to speech coding. At ICASSP98 we presented a system based on an ADPCM scheme with a nonlinear predictor based on a neural net. The most critical parameter was the training procedure in order to achieve good generalization capability and robustness against mismatch between training and testing conditions. In this paper, we propose several new approaches that improve the performance of the original system in up to 1.2dB of SEGSNR (using bayesian regularization). The variance of the SEGSNR between frames is also minimized, so the new scheme produces a more stable quality of the output.