Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Application of an auditory model to speech recognition.

J R Cohen1

  • 1IBM Thomas J. Watson Research Center, Yorktown Heights, New York 10598.

The Journal of the Acoustical Society of America
|June 1, 1989
PubMed
Summary

This study introduces an improved auditory processing front end for speech recognition systems, enhancing adaptation, loudness scaling, and mel warping. The new design demonstrates superior performance compared to prior algorithms.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Chronic cannabis use associated with subcortical topological reorganization of structural connectivity in adults.

Drug and alcohol dependence·2024
Same author

On the apparent stimulation of Candida albicans by chlortetracycline.

Antibiotics & chemotherapy (Northfield, Ill.)·2014
Same author

The embryonic transcription factor Brachyury blocks cell cycle progression and mediates tumor resistance to conventional antitumor therapies.

Cell death & disease·2013
Same author

The effect of early epidural block administration on the progression and outcome of labor.

International journal of obstetric anesthesia·2004
Same author

Journey of a lamb. Walking through dementia together.

Journal of Christian nursing : a quarterly publication of Nurses Christian Fellowship·2002
Same author

Management of the carotid artery in paraganglioma surgery.

Otolaryngologic clinics of North America·2001

Area of Science:

  • Computer Science
  • Signal Processing
  • Acoustics

Background:

  • The IBM speech-recognition system utilizes statistical methods for continuous speech recognition.
  • Auditory processing plays a crucial role in the front-end stages of speech recognition.

Purpose of the Study:

  • To enhance the auditory processing front end of the IBM speech-recognition system.
  • To improve the accuracy and performance of speech recognition algorithms.

Main Methods:

  • Incorporation of adaptation techniques in the auditory processing front end.
  • Implementation of loudness scaling for improved signal representation.
  • Application of mel warping to better model human auditory perception.

Main Results:

  • The new auditory processing front end shows significant improvements over previous algorithms.
  • Specific enhancements include adaptation, loudness scaling, and mel warping.
  • Empirical tests validate the effectiveness of the redesigned system.

Conclusions:

  • The enhanced auditory processing front end represents a notable advancement in speech recognition technology.
  • The integration of adaptation, loudness scaling, and mel warping leads to superior performance.
  • This improved design offers a more robust solution for continuous speech recognition.

Related Experiment Videos