Discriminative language models (DLMs) have been widely used for reranking competing hypotheses produced by an Automatic Speech Recognition (ASR) system. While existing DLMs suffer from limited generalization power, we propose a novel DLM based on a dis-criminatively trained Restricted Boltzmann Machine (RBM). The hidden layer of the RBM improves generalization and allows for employing additional prior knowledge, including pre-trained parameters and entity-related prior. Our approach outperforms the single-layer-perceptron (SLP) reranking model, and fusing our approach with SLP achieves up to 1.3% absolute Word Error Rate (WER) reduction and a relative 180% improvement in terms of WER reduction over the SLP reranker. In particular, it shows that proposed prior informed RBM reranker achieves largest ASR error reduction (3.1% absolute WER) on content words.
展开▼