Speech-driven query retrieval for question-answering

Mobile devices are being used as aids to access a variety of information resources by browsing the Web. However, given their limited screen real estate and soft keyboards, general Web browsing to access information is a tedious task. A system that (a) allows a user to specify their information need as a spoken language query and (b) returns the answer to user's information need directly would be particularly appealing for these devices. In this paper, we address these two problems and present techniques that model question-answering as a query retrieval task. We show that we improve the retrieval accuracy by tightly integrating the constraints of the speech recognition and search components.