F0-based Gammatone Filtering for Intelligibility Gain of Acoustic Noisy Signals

TL;DR

This paper introduces a Gammatone filter-based method in the time domain to enhance speech intelligibility in noisy environments by emphasizing harmonic components, showing significant improvements over baseline techniques.

Contribution

The paper presents a novel F0-based Gammatone filtering approach for speech enhancement, demonstrating its effectiveness through objective intelligibility and quality measures.

Findings

Significant intelligibility gain compared to baseline methods

Improved speech quality as indicated by PESQ and WSS scores

Effective across various non-stationary noise conditions

Abstract

This paper proposes a time-domain method to improve speech intelligibility in noisy scenarios. In the proposed approach, a series of Gammatone filters are adopted to detect the harmonic components of speech. The filters outputs are amplified to emphasize the first harmonics, reducing the masking effects of acoustic noises. The proposed GTFF0 solution and two baseline techniques are examined considering four background noises with different non-stationarity degrees. Three intelligibility measures (ESTOI, ESII and ASIIST) are adopted for objective evaluation. The experiments results show that the proposed scheme leads to expressive speech intelligibility gain when compared to the competing approaches. Furthermore, the PESQ and WSS objective scores demonstrate that the proposed technique also provides interesting quality improvement.