Speech segmentation using multilevel hybrid filters

TL;DR

This paper introduces a new speech segmentation method using multilevel hybrid filters that accurately detects transitions and performs well in noisy environments, enhancing speech coding applications.

Contribution

The paper presents a novel multilevel hybrid filter approach for speech segmentation that improves transition detection and noise robustness over existing methods.

Findings

Accurate transition location detection

Effective in noisy environments (Gaussian and impulsive noise)

Successful application in phonetic speech coding

Abstract

A novel approach for speech segmentation is proposed, based on Multilevel Hybrid (mean/min) Filters (MHF) with the following features: An accurate transition location. Good performance in noisy environments (gaussian and impulsive noise). The proposed method is based on spectral changes, with the goal of segmenting the voice into homogeneous acoustic segments. This algorithm is being used for phoneticallysegmented speech coder, with successful results.