Abstract
Question answering (QA) is probably one of the most challenging tasks in the field of natural language processing. It requires search engines that are capable of extracting concise, precise fragments of text that contain an answer to a question posed by the user. The incorporation of voice interfaces to the QA systems adds a more natural and very appealing perspective for these systems. This paper provides a comprehensive description of current state-of-the-art voice-activated QA systems. Finally, the scenarios that will emerge from the introduction of speech recognition in QA will be discussed. © 2006 IEEE.