The 1st Workshop on Child, Computer and Interaction (WOCCI2008)
Chania, Crete, Greece
Recent advances in SONIC Italian childrens speech recognition will be described. This work, completing a previous one developed in the past, was conducted with the specific goals of integrating the newly trained childrens speech recognition models into the Italian version of the Colorado Literacy Tutor platform. Specifically, childrens speech recognition research for Italian was conducted using the complete training and test set of the ITC-irst Childrens Speech Corpus. Using the University of Colorado SONIC LVSR system, we demonstrate a phonetic recognition error rate of 12,0% for a system which incorporates Vocal Tract Length Normalization (VTLN), Speaker-Adaptive Trained phonetic models, as well as unsupervised Structural MAP Linear Regression (SMAPLR).
Bibliographic reference. Cosi, Piero (2008): "Recent advances in sonic Italian children²s speech recognition for interactive literacy tutors", In WOCCI-2008, paper 02.