Title :
Automatic cry detection in early childhood education settings
Author :
Ruvolo, Paul ; Movellan, Javier
Author_Institution :
Inst. for Neural Comput., Univ. of California San Diego, San Diego, CA
Abstract :
We present results on applying a novel machine learning approach for learning auditory moods in natural environments [1] to the problem of detecting crying episodes in preschool classrooms. The resulting system achieved levels of performance approaching that of human coders and also significantly outperformed previous approaches to this problem [2].
Keywords :
behavioural sciences computing; education; learning (artificial intelligence); auditory moods; automatic cry detection; early childhood education settings; human coders; machine learning; preschool classrooms; Acoustic noise; Deafness; Educational robots; Emotion recognition; Humans; Machine learning; Mood; Prototypes; Robustness; Working environment noise;
Conference_Titel :
Development and Learning, 2008. ICDL 2008. 7th IEEE International Conference on
Conference_Location :
Monterey, CA
Print_ISBN :
978-1-4244-2661-4
Electronic_ISBN :
978-1-4244-2662-1
DOI :
10.1109/DEVLRN.2008.4640830
