An Interesting Property of LPCs for Sonorant Vs Fricative Discrimination

TL;DR

This paper introduces a novel LPC-based feature, T(1), which effectively discriminates sonorants from fricatives with high accuracy and robustness, offering potential applications in speech segmentation and analysis.

Contribution

The paper reveals a new property of LPC coefficients, specifically the inverse tangent of the sum of LPCs, for distinguishing sonorant and fricative speech sounds.

Findings

Achieved 99.07% accuracy on TIMIT database

Demonstrated robustness under additive white noise

Outperformed some existing methods in similar tasks

Abstract

Linear prediction (LP) technique estimates an optimum all-pole filter of a given order for a frame of speech signal. The coefficients of the all-pole filter, 1/A(z) are referred to as LP coefficients (LPCs). The gain of the inverse of the all-pole filter, A(z) at z = 1, i.e, at frequency = 0, A(1) corresponds to the sum of LPCs, which has the property of being lower (higher) than a threshold for the sonorants (fricatives). When the inverse-tan of A(1), denoted as T(1), is used a feature and tested on the sonorant and fricative frames of the entire TIMIT database, an accuracy of 99.07% is obtained. Hence, we refer to T(1) as sonorant-fricative discrimination index (SFDI). This property has also been tested for its robustness for additive white noise and on the telephone quality speech of the NTIMIT database. These results are comparable to, or in some respects, better than the state-of-the-art methods proposed for a similar task. Such a property may be used for segmenting a speech signal or for non-uniform frame-rate analysis.