# Adaptive regularized spectral reduction for stabilizing ill-conditioned bone-conducted speech signals

## TL;DR

This paper introduces a new method to stabilize and improve the analysis of bone-conducted speech signals, which are difficult to process due to their wide frequency range.

## Contribution

The novel regularized spectral reduction (RSR) method compresses frequency ranges and improves linear prediction accuracy for bone-conducted speech.

## Key findings

- RSR effectively reduces eigenvalue spread in bone-conducted speech signals.
- The RSR method outperforms existing techniques in LP analysis for both synthetic and real datasets.
- Improved analysis could benefit hearing aids and voice recognition in noisy environments.

## Abstract

Bone-conducted (BC) speech signals are inherently challenging to analyze due to their wide frequency range, which leads to ill-conditioning in numerical analysis and linear prediction (LP) techniques. This ill-conditioning is primarily caused by the expansion of eigenvalues, which complicates the stability and accuracy of traditional methods. To address this issue, we propose a novel regularized spectral reduction (RSR) method, built upon the regularized least squares (RLS) framework. The RSR method compresses the frequency range of BC speech signals, effectively reducing eigenvalue spread and enhancing the robustness of LP analysis. Key to the RSR approach is a regularization parameter, fine-tuned iteratively to achieve optimal performance. Experimental results demonstrate that RSR significantly outperforms existing techniques in eigenvalue compression, resulting in more accurate LP analysis for both synthetic and real BC speech datasets. These improvements hold promise for applications in hearing aids, voice recognition systems, and speaker identification in noisy environments, where reliable BC speech analysis is critical.