Collaborative Research: CSL-MultiAD: Assessing Collaborative STEM Learning through Rich Information Flow based on Multi-Sensor Audio Diarization

Children's Campus in Kansas City, home to Juniper Gardens

The goal of this project is to develop CSL-MultiAD:MICS a speech and language technology solution which provides assessment of collaborative STEM learning through rich information flow extraction based on multimicrophone audio diarization. Communication based features derived from individual audio streams (word count, talk time, turn-taking, keyword profile) will be extracted through audio Diarization. Leveraged rich information flow from multiple streams in the classroom will be used to develop class based group dynamics. This work will one day offer a communication assessment system for educators to monitor engagement of children with/without intellectual and developmental delays/disabilities using state-of-the art automated speech processing technology.

Project details

  • Primary Investigator: Dwight Irvin

  • Project start Date: 08/01/2019

  • Project finish Date: 07/31/2022



  • National Science Foundation

  • Award Number: IIS-1918012