ADPCM with nonlinear prediction
This work addresses the limitation of linear prediction coding in speech coders for improved signal quality, though it appears incremental as it builds on existing ADPCM frameworks.
The paper tackles the problem of modeling nonlinearities in speech signals by introducing ADPCM schemes with a nonlinear predictor based on neural nets, resulting in a 1-2.5dB increase in SEGSNR over classical methods.
Many speech coders are based on linear prediction coding (LPC), nevertheless with LPC is not possible to model the nonlinearities present in the speech signal. Because of this there is a growing interest for nonlinear techniques. In this paper we discuss ADPCM schemes with a nonlinear predictor based on neural nets, which yields an increase of 1-2.5dB in the SEGSNR over classical methods. This paper will discuss the block-adaptive and sample-adaptive predictions.