Automatic measurement and analysis of the child verbal communication using classroom acoustics within a child care center

Maryam Najafian, Dwight Irvin, Ying Luo, Beth S. Rous, John H.L. Hansen

Research output: Contribution to conferencePaperpeer-review

6 Scopus citations


Understanding the language environment of early learners is a challenging task for both human and machine, and it is critical in facilitating effective language development among young children. This papers presents a new application for the existing diarization systems and investigates the language environment of young children using a turn taking strategy employing an i-vector based baseline that captures adult-to-child or child-tochild conversational turns across different classrooms in a child care center. Detecting speaker turns is necessary before more in depth subsequent analysis of audio such as word count, speech recognition, and keyword spotting which can contribute to the design of future learning spaces specifically designed for typically developing children, or those at-risk with communication limitations. Experimental results using naturalistic childteacher classroom settings indicate the proposed rapid childadult speech turn taking scheme is highly effective under noisy classroom conditions and results in 27.3% relative error rate reduction compared to the baseline results produced by the LIUM diarization toolkit.

Original languageEnglish
Number of pages6
StatePublished - 2016
Event5th International Workshop on Child Computer Interaction, WOCCI 2016 - San Francisco, United States
Duration: Sep 6 2016Sep 7 2016


Conference5th International Workshop on Child Computer Interaction, WOCCI 2016
Country/TerritoryUnited States
CitySan Francisco

Bibliographical note

Funding Information:
Received July 13, 2016; revised Nov. 18, 2016; accepted Dec. 2, 2016. Authorcontributions:Y.Liu,Z.L.-J.,J.W.,M.P.M.,L.-J.W.,andX.-G.L.designedresearch;Y.Liu,Z.L.-J.,J.W.,D.L., W.R., J.P., X.W., T.X., W.X., R.P., Y. Li, and M.M. performed research; Y. Liu, Z.L.-J., J.W., and Z.-H.Q. contributed unpublished reagents/analytic tools; Y. Liu, Z.L.-J., J.W., D.L., and W.R. analyzed data; Y. Liu, Z.L.-J., J.W., M.P.M., L.-J.W., and X.-G.L. wrote the paper. This work was supported by the National Natural Science Foundation of China (Grants U1201223, 81200856, 30970957, 81371198, and 31000489), the National Institutes of Health (Grants R01NS088627 and R21DE025689), and the Intramural Research Program of the National Institute on Aging. We thank Dr. Wen-Biao Gan for providing CX3CR1 CreER/+ mice and Huai-Yu Gu for technical support. The authors declare no competing financial interests. *Y.L., L.-J.Z., and J.W. contributed equally to this work. Correspondence should be addressed to either of the following: Xian-Guo Liu, Pain Research Center and Department of Physiology, Zhongshan School of Medicine of Sun Yat-sen University, Guangzhou 510080, China, E-mail: or Long-Jun Wu, Rutgers University, Piscataway, NJ 08854. E-mail: DOI:10.1523/JNEUROSCI.2235-16.2016 Copyright © 2017 the authors 0270-6474/17/370872-11$15.00/0

Publisher Copyright:
© 2016 5th Workshop on Child Computer Interaction, WOCCI 2016. All rights reserved.


  • child speech
  • language environment analysis
  • speech turn taking

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Software
  • Computer Science Applications


Dive into the research topics of 'Automatic measurement and analysis of the child verbal communication using classroom acoustics within a child care center'. Together they form a unique fingerprint.

Cite this