A new subband non linear prediction coding algorithm for narrowband speech signal: The nADPCMB MLT coding scheme

TL;DR

This paper introduces a novel narrowband speech coding algorithm that combines subband decomposition with neural network-based non-linear prediction, enhancing speech compression quality.

Contribution

It presents a new subband non-linear prediction coding algorithm using neural networks and MLT filter bank for improved narrowband speech coding.

Findings

Evaluated with formal listening tests using ITU-T P.800 scale.

Demonstrates improved speech quality over traditional methods.

Introduces neural network-based non-linear prediction in subband coding.

Abstract

This paper focuses on a newly developed transparent nADPCMB MLT speech coding algorithm. Our coder first decomposes the narrowband speech signal in subbands, a non linear ADPCM scheme is then performed in each subband. The signal subband decomposition is piloted by the equivalent Modulated Lapped Transform (MLT) filter bank. The novelty of this algorithm is the non linear approach, based on neural networks, to subband prediction coding. We have evaluated the performance of the nADPCMB MLT coding algorithm with a session of formal listening based on the five grade impairment scale standardized within ITU - T Recommendation P.800.