Mobile voice search is a fast-growing business. It provides users an easier way to search for information using voice from mobile devices. In this paper, we describe a statistical approach to query parsing to assure search effectiveness. The task is to segment speech recognition (ASR) output, including ASR 1-Best and ASR word lattices, into segments and associate each segment with needed concepts in the application. We train the models including concept prior probability, query segment generation probability, and query subject probability from application data such as query log and source database. We apply the learned models on a mobile business search application and demonstrate the robustness of query parsing to ASR errors.
展开▼
