The Human Speechome Project

Philip DeCamp, Michael Fleischman, Peter Gorniak, Jethran Guinness, Rony Kubat, Michael Levit, Nikolaos Mavridis, Rupal Patel, Brandon Roy, Deb Roy, Stefanie Tellex, Alexia Salata

Abstract

The Human Speechome Project is an effort to observe and computationally model the longitudinal course of language development of a single child at an unprecedented scale.The idea is this: Instrument a child's home so that nearly everything the child hears and sees from birth to three is recorded.Develop a computational model of language learning that takes the child's audio-visual experiential record as input.Evaluate the model's performance in matching the child's linguistic abilities as a means of assessing possible learning strategies used by children in natural contexts.First steps of a pilot effort along these lines are described including issues of privacy management and methods for overcoming limitations of fully-automated machine perception.
BibTeX
@inproceedings{decamp2006human,
  author = {Philip DeCamp and Michael Fleischman and Peter Gorniak and Jethran Guinness and Rony Kubat and Michael Levit and Nikolaos Mavridis and Rupal Patel and Brandon Roy and Deb Roy and Stefanie Tellex and Alexia Salata},
  title = {{The Human Speechome Project}},
  booktitle = {EELC},
  year = {2006},
  doi = {10.1007/11880172\_15},
}

Loading related content...

Figure