Multimedia Tools and Applications

, Volume 54, Issue 2, pp 291–319

Low-complexity F0-based speech/nonspeech discrimination approach for digital hearing aids

Authors

  • Pablo Cabañas Molero
    • Department of Telecommunication EngineeringUniversity of Jaén, Polytechnic School
    • Department of Telecommunication EngineeringUniversity of Jaén, Polytechnic School
  • Pedro Vera Candeas
    • Department of Telecommunication EngineeringUniversity of Jaén, Polytechnic School
  • Saturnino Maldonado Bascon
    • Department of Signal Theory and CommunicationsUniversity of Alcalá, Polytechnic School
Article

DOI: 10.1007/s11042-010-0523-1

Cite this article as:
Cabañas Molero, P., Ruiz Reyes, N., Vera Candeas, P. et al. Multimed Tools Appl (2011) 54: 291. doi:10.1007/s11042-010-0523-1

Abstract

Digital hearing aids impose strong complexity and memory constraints on digital signal processing algorithms that implement different applications. This paper proposes a low complexity approach for automatic sound classification in digital hearing aids. The proposed scheme, which operates on a frame-by-frame basis, consists of two stages: analysis stage and classification stage. The analysis stage provides a set of low-complexity signal features derived from fundamental frequency (F0) estimation. Here, F0 estimation is performed by a decimated difference function, which results in a reduced-complexity analysis stage. The classification stage has been designed with the aim of reducing the complexity while maintaining high accuracy rates. Three low-complexity classifiers have been evaluated (tree-based C4.5, 1-Nearest Neighbor (1-NN) and a Multilayer Perceptron (MLP)), the MLP being chosen because it provides the best accuracy rates and fits to the computational and memory constraints of ultra low-power DSP-based hearing aids. The classification stage is composed of a MLP classifier followed by a Hidden Markov Model (HMM), providing a good trade-off solution between complexity and classification accuracy rate. The goal of the proposed approach is to perform a robust discrimination among speech/nonspeech parts of audio signals in commercial digital hearing aids, the computational cost being a critical issue. For the experiments, an audio database including speech, music and noise signals has been used.

Keywords

Fundamental frequency estimation Automatic sound classification Digital hearing aids Difference function Multilayer perceptron Hidden Markov model

Copyright information

© Springer Science+Business Media, LLC 2010