To satisfy the average user, a voice interface to a search engine must recognize spoken queries, and must return highly relevant search results. Several problems exist in designing satisfactory voice interfaces. Current speech recognition technology has high word error rates for large vocabulary sizes. There is very little repetition in queries, providing little information that could be used to guide the speech recognizer.
While the patent isn’t specifically focused on mobile search technologies, I wonder how this news will go over locally with the companies working in that area. Those include Medio Systems, InfoSpace, Microsoft (through its recently announced acquisition of Paris-based MotionBridge) and particularly VoiceBox Technologies. Action Engine is also developing a mobile application platform and looking at data entry on mobile devices.