Semantic data selection for vertical business voice search
With the exponential growth in the number of mobile devices, voice enabled local search is emerging as one of the most popular applications. Although the application is essentially an integration of automatic speech recognition (ASR) and text or database search, the potential usefulness of this application has been widely acknowledged. In this paper, we present a data-driven approach to voice query parsing, that segments the input query into several fields that are necessary for high-precision local search. We also demonstrate the robustness of our approach to ASR errors. We present an approach for exploiting multiple hypotheses from ASR, in the form of word confusion networks, in order to achieve tighter coupling between ASR and query parsing. A confusion-network based query parsing outperforms ASR 1-best based query-parsing by 2.6% absolute.