Preprocessing and Segmentation of the Speech Signal in the Frequency Domain for Speech Recognition

  • Authors:

  • A. S. Kolokolov

  • Affiliations:

  • Trapeznikov Institute of Control Sciences, Russian Academy of Sciences, Moscow, Russia

  • Venue:
  • Automation and Remote Control
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

Preprocessing of the speech signal before recognition of phonemes was considered. Methods of processing the spectrum and segmenting the speech signal for stable speech recognition in the presence of frequency distortions were proposed. They are based on a procedure of linear filtering of the logarithmic spectrum envelope.