Automated Assessment of Child Vocalization Development Using LENA Purpose To produce a novel, efficient measure of children's expressive vocal development on the basis of automatic vocalization assessment (AVA), child vocalizations were automatically identified and extracted from audio recordings using Language Environment Analysis (LENA) System technology. Method Assessment was based on full-day audio recordings collected in a ... Research Article
Research Article  |   July 12, 2017
Automated Assessment of Child Vocalization Development Using LENA
 
Author Affiliations & Notes
  • Jeffrey A. Richards
    LENA Research Foundation, Boulder, CO
  • Dongxin Xu
    LENA Research Foundation, Boulder, CO
    University of Colorado, Boulder
  • Jill Gilkerson
    LENA Research Foundation, Boulder, CO
    University of Colorado, Boulder
  • Umit Yapanel
    InvenSense, San Jose, CA
  • Sharmistha Gray
    Nuance Communications, Burlington, MA
  • Terrance Paul
    LENA Research Foundation, Boulder, CO
  • Disclosure: J. A. Richards, D. Xu, J. Gilkerson, and T. Paul are affiliated with LENA Research Foundation, which funded the study. The other authors have declared that no competing interests existed at the time of publication.
    Disclosure: J. A. Richards, D. Xu, J. Gilkerson, and T. Paul are affiliated with LENA Research Foundation, which funded the study. The other authors have declared that no competing interests existed at the time of publication. ×
  • Correspondence to Jeffrey A. Richards: JeffRichards@LENA.org
  • Editor: Sean Redmond
    Editor: Sean Redmond×
  • Associate Editor: Navin Viswanathan
    Associate Editor: Navin Viswanathan×
Article Information
Speech, Voice & Prosody / Language / Research Articles
Research Article   |   July 12, 2017
Automated Assessment of Child Vocalization Development Using LENA
Journal of Speech, Language, and Hearing Research, July 2017, Vol. 60, 2047-2063. doi:10.1044/2017_JSLHR-L-16-0157
History: Received April 17, 2016 , Revised October 10, 2016 , Accepted January 25, 2017
 
Journal of Speech, Language, and Hearing Research, July 2017, Vol. 60, 2047-2063. doi:10.1044/2017_JSLHR-L-16-0157
History: Received April 17, 2016; Revised October 10, 2016; Accepted January 25, 2017

Purpose To produce a novel, efficient measure of children's expressive vocal development on the basis of automatic vocalization assessment (AVA), child vocalizations were automatically identified and extracted from audio recordings using Language Environment Analysis (LENA) System technology.

Method Assessment was based on full-day audio recordings collected in a child's unrestricted, natural language environment. AVA estimates were derived using automatic speech recognition modeling techniques to categorize and quantify the sounds in child vocalizations (e.g., protophones and phonemes). These were expressed as phone and biphone frequencies, reduced to principal components, and inputted to age-based multiple linear regression models to predict independently collected criterion-expressive language scores. From these models, we generated vocal development AVA estimates as age-standardized scores and development age estimates.

Result AVA estimates demonstrated strong statistical reliability and validity when compared with standard criterion expressive language assessments.

Conclusions Automated analysis of child vocalizations extracted from full-day recordings in natural settings offers a novel and efficient means to assess children's expressive vocal development. More research remains to identify specific mechanisms of operation.

Acknowledgments
This research was funded by the LENA Research Foundation, a nonprofit 501(c)(3) public charity. We gratefully acknowledge the Paul family for their wisdom and philanthropy, without which none of this work would have been possible. We would also like to express our deep appreciation to the families who participated.
Order a Subscription
Pay Per View
Entire Journal of Speech, Language, and Hearing Research content & archive
24-hour access
This Article
24-hour access