CRF-based Stochastic Pronunciation Modeling for Out-of-Vocabulary Spoken Term Detection

Dong Wang - Post Doc
Multimedia Communications

Date: September 20th 2010
Location: Eurecom - Eurecom

Out-of-vocabulary (OOV) terms present a significant challenge to spoken term detection (STD). This challenge, to a large extent, lies in the high degree of uncertainty in pronunciations of OOV terms. In previous work, we presented a stochastic pronunciation modeling (SPM) approach to compensate for this uncertainty. A shortcoming of our original work, however, is that the SPM was based on a joint-multigram model (JMM), which is suboptimal. In this paper, we propose to use conditional random fields (CRFs) for letter-to-sound conversion, which significantly improves quality of the predicted pronunciations. When applied to OOV STD, we achieve considerable performance improvement with both a 1-best system and an SPM-based system.

Permalink: https://www.eurecom/seminar/19725