Natural number recognition using MCE trained inter-word context dependent acoustic models

Abstract

Among applications that require number recognition, the focus has largely been on connected digit recognizers. In this paper, we introduce an acoustic model topology for natural number recognition by using minimum classification error (MCE) training of inter-word context dependent models of the head-body-tail (HBT) type. Experimental results on natural… (More)
DOI: 10.1109/ICASSP.1998.674466

2 Figures and Tables

Topics

  • Presentations referencing similar topics