Speech recognition by humans and machines under conditions with severe channel variability and noise

Richard P. Lippmann; Beth A. Carlson

doi:10.1117/12.271525

4 April 1997 Speech recognition by humans and machines under conditions with severe channel variability and noise

Richard P. Lippmann, Beth A. Carlson

Proceedings Volume 3077, Applications and Science of Artificial Neural Networks III; (1997) https://doi.org/10.1117/12.271525
Event: AeroSense '97, 1997, Orlando, FL, United States

Abstract

Despite dramatic recent advances in speech recognition technology, speech recognition still perform much worse than humans. The difference in performance between humans and machines is most dramatic when variable amounts and types of filtering and noise are present during testing. For example, humans readily understand speech that is low-pass filtered below 3 kHz or high-pass filtered above 1 kHz. Machines trained with wide-band speech, however, degrade dramatically under these conditions. An approach to compensate for variable unknown sharp filtering and noise is presented which uses mel-filter-bank magnitudes as input features, estimates the signal-to-noise ratio (SNR) for each filter, and uses missing feature theory to dynamically modify the probability computations performed using Gaussian Mixture or Radial Basis Function neural network classifiers embedded within Hidden Markov Model recognizers. The approach was successfully demonstrated using a talker-independent digit recognition task. It was found that recognition accuracy across many conditions rises from below 50% to above 95% with this approach. These promising results suggest future work to dynamically estimate SNR's and to explore the dynamics of human adaptation to channel and noise variability.

Citation Download Citation

Richard P. Lippmann and Beth A. Carlson "Speech recognition by humans and machines under conditions with severe channel variability and noise", Proc. SPIE 3077, Applications and Science of Artificial Neural Networks III, (4 April 1997); https://doi.org/10.1117/12.271525

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available