THE JOHNS HOPKINS UNIVERSITY Sub-Lexical and Contextual Modeling of Out-of-Vocabulary Words in Speech Recognition

Large vocabulary speech recognition systems fail to recognize words beyond their vocabulary, many of which are information rich terms, like named entities or foreign words. Hybrid word/sub-word systems solve this problem by adding sub-word units to large vocabulary word based systems; new words can then be represented by combinations of subword units. We present a novel probabilistic model to learn the sub-word lexicon optimized for a given task. We consider the task of Out Of vocabulary (OOV) word detection, which relies on output from a hybrid system. We combine the proposed hybrid system with confidence based metrics to improve OOV detection performance. Previous work address OOV detection as a binary classification task, where each region is independently classified using local information. We propose to treat OOV detection as a sequence labeling problem, and we show that 1) jointly predicting out-of-vocabulary regions, 2) including contextual information from each region, and 3) learning sub-lexical units optimized for this task, leads to substantial improvements with respect to state-of-the-art on an English Broadcast News and MIT Lectures task.