Improved Discriminative Training Using Phone Lattices

Abstract

We present an efficient discriminative training procedure utilizing phone lattices. Different approaches to expediting lattice generation, statistics collection, and convergence were studied. We also propose a new discriminative training criterion, namely, minimum phone frame error (MPFE). When combined with the maximum mutual information (MMI) criterion using I-smoothing, replacing the standard minimum phone error (MPE) criterion with MPFE led to a small but consistent win in several applications. Phone-lattice-based discriminative training gave around 8 pct to 12 pct relative word error rate (WER) reduction in SRI’s latest English Conversational Telephone Speech and Broadcast News transcription systems developed for DARPA’s EARS project.