TITLE

An Auditory-Feedback-Based Neural Network Model of Speech Production That Is Robust to Developmental Changes in the Size and Shape of the Articulatory System

AUTHOR(S)
Callan, Daniel E.; Kent, Ray D.; Guenther, Frank H.; Vorperian, Houri K.
PUB. DATE
June 2000
SOURCE
Journal of Speech, Language & Hearing Research;Jun2000, Vol. 43 Issue 3, p721
SOURCE TYPE
Academic Journal
DOC. TYPE
Article
ABSTRACT
The purpose of this article is to demonstrate that self-produced auditory feedback is sufficient to train a mapping between auditory target space and articulator space under conditions in which the structures of speech production are undergoing considerable developmental restructuring. One challenge for competing theories that propose invariant constriction targets is that it is unclear what teaching signal could specify constriction location and degree so that a mapping between constriction target space and articulator space can be learned. It is predicted that a model trained by auditory feedback will accomplish speech goals, in auditory target space, by continuously learning to use different articulator configurations to adapt to the changing acoustic properties of the vocal tract during development. The Maeda articulatory synthesis part of the DIVA neural network model (Guenther et al., 1998) was modified to reflect the development of the vocal tract by using measurements taken from MR images of children. After training, the model was able to maintain the 11 English vowel targets in auditory planning space, utilizing varying articulator configurations, despite morphological changes that occur during development. The vocal-tract constriction pattern (derived from the vocal-tract area function) as well as the formant values varied during the course of development in correspondence with morphological changes in the structures involved with speech production. Despite changes in the acoustical properties of the vocal tract that occur during the course of development, the model was able to demonstrate motor-equivalent speech production under lip-restriction conditions. The model accomplished this in a self-organizing manner even though there was no prior experience with lip restriction during training.
ACCESSION #
3226702

 

Related Articles

  • Frequency modulations in the speech signal. Leonov, A. S.; Makarov, I. S.; Sorokin, V. N. // Acoustical Physics;Nov2009, Vol. 55 Issue 6, p876 

    The paper examines physical mechanisms of frequency modulations in acoustics of the vocal tract and methods of estimation of these modulations in the speech signal. It has been found that vibrations of the tract walls make a negligibly small effect on modulations of its resonance frequencies....

  • Vocal tract area function estimation from midsagittal dimensions with CT scans and a vocal tract... Perrier, P.; Boe, L. // Journal of Speech & Hearing Research;Feb92, Vol. 35 Issue 1, p53 

    Presents a model which shows the generation of area functions from measurements of the sagittal section, which is an important step in the study of the relation between vocal tract geometry and speech acoustics. The model is based on analysis ofa vocal tract cast for large sagittal dimensions...

  • SPEECH Dances of the Vocal Tract. Goldstein, Louis; Rubin, Philip // Odyssey;Jan2007, Vol. 16 Issue 1, p14 

    The article discusses the role of vocal tract in the production of speech.

  • The response to sudden change in vocal tract resistance during stop consonant production. Kim, Jong-Ryoul; Zajac, David J. // Journal of Speech, Language & Hearing Research;Aug1997, Vol. 40 Issue 4, p848 

    Investigates responses to sudden change in vocal tract resistance during stop consonant production. Ability of the speech respiratory system to adapt to changes in the airway environment; Rapid occurrence of compensatory respiratory responses to suprathreshold pressure-venting after valve...

  • How children learn to organize their speech gestures: Further evidence from fricative-vowel... Nittrouer, Susan; Studdert-Kennedy, Michael // Journal of Speech & Hearing Research;Apr96, Vol. 39 Issue 2, p379 

    Studies the production of fricative-vowel syllables in children's speech. Difference in the overall spectrum between fricatives in children's and adult's speech; Role of age-related difference in vocal-tract geometry on age-related difference in vowel effects on fricative noise; Difference...

  • Speech science.  // ASHA;Oct94, Vol. 36 Issue 10, p60 

    Presents activities of the American Speech-Language-Hearing Association (ASHA) on speech science for November 18, 1994 at the 1994 ASHA Convention. Developments in Vocal Tract Estimation; Perception of Acoustically Altered CVCs by Black English-Speaking Children; A Comparison of Vocal Stress in...

  • Perceptual Gender Identity of Voices in Pre-pubertal children. Duvvuru, Sirisha; Sreedevi, N. // Journal of the All India Institute of Speech & Hearing;2009, Vol. 28, p54 

    The present study investigated sexual dimorphism in voices of children. Ten children each in the age group of 4-5 years and 5-6 years participated in the study. Listener's identification of gender in phonation and speech tasks were obtained. Results revealed that gender identification was better...

  • Visual Influences on Perception of Speech and Nonspeech Vocal-Tract Events. Brancazio, Lawrence; Best, Catherine T.; Fowler, Carol A. // Language & Speech;Mar2006, Vol. 49 Issue 1, p21 

    We report four experiments designed to determine whether visual information affects judgments of acoustically-specified nonspeech events as well as speech events (the "McGurk effect"). Previous findings have shown only weak McGurk effects for nonspeech stimuli, whereas strong effects are found...

  • Modified Mfcc for Speaker Recognition. Vaskas, Alireza Salahshour; Esfandiyari, Ahmad; Shamshirband, Shahaboddin // Australian Journal of Basic & Applied Sciences;2010, Vol. 4 Issue 9, p4357 

    In this research is described a method for feature extraction from the signal that is based on the MFCC analysis. The researchers discover that the major fraction of the speech information is in the low frequency and the information in high frequency is very rubbish. So they make a method that...

Share

Read the Article

Courtesy of VIRGINIA BEACH PUBLIC LIBRARY AND SYSTEM

Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics