Paper ID: 2203.01819

Speech segmentation using multilevel hybrid filters

Marcos Faundez-Zanuy, Francesc Vallverdu-Bayes

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.

Submitted: Feb 24, 2022