Vowel Classification Based on Fundamental Frequency and Formant Frequencies A quadratic discriminant classification technique was used to classify spectral measurements from vowels spoken by men, women, and children. The parameters used to train the discriminant classifier consisted of various combinations of fundamental frequency and the three lowest formant frequencies. Several nonlinear auditory transforms were evaluated. Unlike previous studies using ... Research Article
Research Article  |   August 01, 1993
Vowel Classification Based on Fundamental Frequency and Formant Frequencies
 
Author Affiliations & Notes
  • James Hillenbrand
    Western Michigan University, Kalamazoo
  • Robert T. Gayvert
    RIT Research Corporation Rochester, NY
  • Contact author: James Hillenbrand, Department of Speech Pathology and Audiology, Western Michigan University, Kalamazoo, MI 49008.
Article Information
Speech, Voice & Prosody / Speech / Research Articles
Research Article   |   August 01, 1993
Vowel Classification Based on Fundamental Frequency and Formant Frequencies
Journal of Speech, Language, and Hearing Research, August 1993, Vol. 36, 694-700. doi:10.1044/jshr.3604.694
History: Received September 29, 1992 , Accepted March 17, 1993
 
Journal of Speech, Language, and Hearing Research, August 1993, Vol. 36, 694-700. doi:10.1044/jshr.3604.694
History: Received September 29, 1992; Accepted March 17, 1993

A quadratic discriminant classification technique was used to classify spectral measurements from vowels spoken by men, women, and children. The parameters used to train the discriminant classifier consisted of various combinations of fundamental frequency and the three lowest formant frequencies. Several nonlinear auditory transforms were evaluated. Unlike previous studies using a linear discriminant classifier, there was no advantage in category separability for any of the nonlinear auditory transforms over a linear frequency scale, and no advantage for spectral distances over absolute frequencies. However, it was found that parameter sets using nonlinear transforms and spectral differences reduced the differences between phonetically equivalent tokens produced by different groups of talkers.

Acknowledgments
This work was supported by the Air Force Systems Command, Rome Air Development Center, Griffiss Air Force Base, and the Air Force Office of Scientific Research (Contract No. F30602-85-C-0008), and by a research grant from the National Institutes of Health (NIDCD 1-R01-DC01661).
Order a Subscription
Pay Per View
Entire Journal of Speech, Language, and Hearing Research content & archive
24-hour access
This Article
24-hour access