CIS-BWE: Chaos-Informed Speech Bandwidth Extension

TL;DR

This paper introduces NDSI-BWE, a novel chaos-informed adversarial framework for speech bandwidth extension that leverages multiple discriminators inspired by nonlinear dynamical systems to improve high-frequency component recovery.

Contribution

It presents a new framework with seven chaos-inspired discriminators and a complex-valued ConformerNeXt generator, achieving state-of-the-art results in speech bandwidth extension.

Findings

Achieves new state-of-the-art performance in BWE across six metrics.

Reduces parameters by eight times using depth-wise convolution.

Outperforms previous methods in subjective human evaluations.

Abstract

Recovering high-frequency components lost to bandwidth constraints is crucial for applications ranging from telecommunications to high-fidelity audio on limited resources. We introduce NDSI-BWE, a new adversarial Band Width Extension (BWE) framework that leverage four new discriminators inspired by nonlinear dynamical system to capture diverse temporal behaviors: a Multi-Resolution Lyapunov Discriminator (MRLD) for determining sensitivity to initial conditions by capturing deterministic chaos, a Multi-Scale Recurrence Discriminator (MS-RD) for self-similar recurrence dynamics, a Multi-Scale Detrended Fractal Analysis Discriminator (MSDFA) for long range slow variant scale invariant relationship, a Multi-Resolution Poincar\'e Plot Discriminator (MR-PPD) for capturing hidden latent space relationship, a Multi-Period Discriminator (MPD) for cyclical patterns, a Multi-Resolution Amplitude Discriminator (MRAD) and Multi-Resolution Phase Discriminator (MRPD) for capturing intricate amplitude-phase transition statistics. By using depth-wise convolution at the core of the convolutional block with in each discriminators, NDSI-BWE attains an eight-times parameter reduction. These seven discriminators guide a complex-valued ConformerNeXt based genetor with a dual stream Lattice-Net based architecture for simultaneous refinement of magnitude and phase. The genertor leverage the transformer based conformer's global dependency modeling and ConvNeXt block's local temporal modeling capability. Across six objective evaluation metrics and subjective based texts comprises of five human judges, NDSI-BWE establishes a new SoTA in BWE.