Abstract

In this paper, we use information retrieval (IR) techniques to im-prove a speech recognition (ASR) system. The potential benefits include improved speed, accuracy, and scalability. Where conven-tional HMM-based speech recognition systems decode words di-rectly, our IR-based system first decodes subword units. These are then mapped to a target word by the IR system. In this decoupled system, the IR serves as a lightweight, data-driven pronunciation model. Our proposed method is evaluated in the Windows Live Search for Mobile (WLS4M) task, and our best system has 12% fewer errors than a comparable HMM classifier. We show that even using an inexpensive IR weighting scheme (TF-IDF) yields a 3% relative error rate reduction while maintaining all of the advantages of the IR approach.