Heterogeneous measurements and multiple classifiers for speech recognition.

TLDR: In context-independent classification and context-dependent recognition on the TIMIT core test set using 39 classes, the system achieved error rates that are the lowest the authors have seen reported on these tasks.

Abstract: This paper addresses the problem of acoustic phonetic modeling. First, heterogeneous acoustic measurements are chosen in order to maximize the acoustic-phonetic information extracted from the speech signal in preprocessing. Second, classifier systems are presented for successfully utilizing high-dimensional acoustic measurement spaces. The techniques used for achieving these two goals can be broadly categorized as hierarchical, committeebased, or a hybrid of these two. This paper presents committeebased and hybrid approaches. In context-independent classification and context-dependent recognition on the TIMIT core test set using 39 classes, the system achieved error rates of 18.3% and 24.4%, respectively. These error rates are the lowest we have seen reported on these tasks. In addition, experiments with a telephone-based weather information word recognition task led to word error rate reductions of 10–16%.