Advertisement

Automatic Speech Recognition

  • Peter Schäuble
Part of the The Springer International Series in Engineering and Computer Science book series (SECS, volume 397)

Abstract

Sound waves in general and speech in particular consist of disturbances traveling through the air. These disturbances are described by the air displacement, air density, and air pressure. All of these quantities are time and space dependent. Sound waves have the following properties which may be either confirmed experimentally or derived from physical laws:
  • ■ The speed of a sound wave depends on the temperature and weight of the gas molecules. Given the temperature and weight of the molecules, a changes in air density or in pressure do not affect the speed of sound waves.

  • ■ Sound waves satisfy the superposition principle, i.e. the superposition of several sound waves is a sound wave. This principle implies that two sound waves coming from opposite directions can travel through each other without loss.

Keywords

Speech Recognition Discrete Fourier Transform Vocal Tract Output Probability Critical Band 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Note

  1. 1.
    We use here the ARPAbet in contrast to the SAMPA alphabet which we use below for German speech recognition.Google Scholar

Copyright information

© Springer Science+Business Media New York 1997

Authors and Affiliations

  • Peter Schäuble
    • 1
  1. 1.Swiss Federal Institute of Technology (ETH)ZurichSwitzerland

Personalised recommendations