Perceptive, non-linear speech processing and spiking neural networks

  • Authors:
  • Jean Rouat;Ramin Pichevar;Stéphane Loiselle

  • Affiliations:
  • Université de Sherbrooke;Université de Sherbrooke;Université de Sherbrooke

  • Venue:
  • Nonlinear Speech Modeling and Applications
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

Source separation and speech recognition are very difficult in the context of noisy and corrupted speech. Most conventional techniques need huge databases to estimate speech (or noise) density probabilities to perform separation or recognition. We discuss the potential of perceptive speech analysis and processing in combination with biologically plausible neural network processors. We illustrate the potential of such non-linear processing of speech on a source separation system inspired by an Auditory Scene Analysis paradigm. We also discuss a potential application in speech recognition.