22. Feature Extraction for ASR

  1. Ben Gold1,
  2. Nelson Morgan2 and
  3. Dan Ellis3

Published Online: 14 OCT 2011

DOI: 10.1002/9781118142882.ch22

Speech and Audio Signal Processing: Processing and Perception of Speech and Music, Second Edition

Speech and Audio Signal Processing: Processing and Perception of Speech and Music, Second Edition

How to Cite

Gold, B., Morgan, N. and Ellis, D. (2011) Feature Extraction for ASR, in Speech and Audio Signal Processing: Processing and Perception of Speech and Music, Second Edition, John Wiley & Sons, Inc., Hoboken, NJ, USA. doi: 10.1002/9781118142882.ch22

Author Information

  1. 1

    Massachusetts Institute of Technology, Lincoln Laboratory

  2. 2

    International Computer Science Institute and University of California at Berkeley

  3. 3

    Columbia University and International Computer Science Institute

Publication History

  1. Published Online: 14 OCT 2011
  2. Published Print: 15 AUG 2011

ISBN Information

Print ISBN: 9780470195369

Online ISBN: 9781118142882

SEARCH

Keywords:

  • common feature vectors;
  • robustness;
  • convolutional error;
  • room reverberation;
  • auditory models

Summary

This chapter contains sections titled:

  • Introduction

  • Common Feature Vectors

  • Dynamic Features

  • Strategies for Robustness

  • Auditory Models

  • Multichannel Input

  • Discriminant Features

  • Discussion

  • Exercises