Speech recognition using randomized relational decision trees

We explore the possibility of recognizing speech signals using a large collection of coarse acoustic events, which describe temporal relations between a small number of local features of the spectrogram. The major issue of invariance to changes in duration of speech signal events is addressed by defining temporal relations in a rather coarse manner, allowing for a large degree of slack. The approach is greedy in that it does not offer an “explanation” of the ∗Supported in part by the Army Research Office under grant DAAH04-96-1-0061 and MURI grant DAAH04-96-1-0445, †Supported in part by the University of Chicago Block Fund.