English

Speech segmentation using multilevel hybrid filters

Audio and Speech Processing 2022-03-04 v1 Machine Learning Sound

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.

Keywords

Cite

@article{arxiv.2203.01819,
  title  = {Speech segmentation using multilevel hybrid filters},
  author = {Marcos Faundez-Zanuy and Francesc Vallverdu-Bayes},
  journal= {arXiv preprint arXiv:2203.01819},
  year   = {2022}
}

Comments

4 pages

R2 v1 2026-06-24T10:01:04.257Z