Adaptive hybrid speech coding with a MLP LPC structure

TL;DR

This paper introduces an adaptive hybrid speech coding scheme combining linear predictive coding and neural networks, achieving improved speech quality with lower bitrates.

Contribution

It presents a novel combined linear/nonlinear predictive model for speech coding that enhances performance over traditional methods.

Findings

Improved SEGSNR by 1 to 2.5 dB with adaptive quantization

Effective integration of LPC and neural nets in speech coding

Demonstrated benefits of nonlinear models in real applications

Abstract

In the last years there has been a growing interest for nonlinear speech models. Several works have been published revealing the better performance of nonlinear techniques, but little attention has been dedicated to the implementation of the nonlinear model into real applications. This work is focused on the study of the behaviour of a combined linear/nonlinear predictive model based on linear predictive coding (LPC-10) and neural nets, in a speech waveform coder. Our novel scheme obtains an improvement in SEGSNR between 1 and 2.5 dB for an adaptive quantization ranging from 2 to 5 bits.