Abstract: Techniques for performing spoken language understanding (SLU) processing on a device are described. Example embodiments involve a device determining whether a spoken input corresponds to a supported spoken input class, a supported spoken input with dynamic content class or an unsupported spoken input class. For a spoken input corresponding to the supported spoken input with dynamic content class, the device may determine an entity corresponding to the spoken input from a set of entities, which may be determined based on device context data and/or user profile data. For a spoken input corresponding to the supported spoken input class, the device may determine an intent and entity using stored data. For a spoken input corresponding to the unsupported spoken input class, the device may send the audio data to a system for processing.

Abstract: A method of constructing a three-dimensional image from a plurality of two-dimensional images is comprised of the steps of selecting one of the images to be a reference image and selecting a second image. One or more points in the second image are identified as possible match points for each point in the reference image. The other images are used to verify the possible match points found in the second image. The projections of the possible match points are grouped into three-dimensional regions, and the regions are projected onto the reference image for the purpose of identifying false regions. The false region are eliminated and a three-dimensional image is constructed by combining the remaining regions.