Find some of the recent patent filings from Microsoft that became public.
Speech recognition techniques are disclosed herein. In one embodiment, a novice mode is available such that when the user is unfamiliar with the speech recognition system, a voice user interface (VUI) may be provided to guide them. The VUI may display one or more speech commands that are presently available. The VUI may also provide feedback to train the user. After the user becomes more familiar with speech recognition, the user may enter speech commands without the aid of the novice mode. In this “experienced mode,” the VUI need not be displayed. Therefore, the user interface is not cluttered.
A 3D camera for determining distances to regions in a scene wherein gating or modulating apparatus for the 3D camera is incorporated on a photosurface of the camera on which light detectors of the camera are also situated. Each pixel in the photosurface may include its own pixel circuit for gating the pixel on or off or for modulating the sensitivity of the pixel to incident light. The circuit may comprise at least one amplifier inside the pixel, at least one feedback capacitor separate from the light sensitive element and connected between the input and output of each of the at least one amplifier, and at least one controllable connection through which current flows from the light sensitive element into the input of the at least one amplifier. The 3D camera may further include a light source and a controller.
A route planning system comprises a receiver component that receives a request for directions between a beginning point and a destination point. An analysis component analyzes a traffic system representation that varies as context varies and outputs expected amounts of travel time between the beginning point and the destination point for multiple contexts based at least in part upon the analysis. A method is described herein that includes techniques for searching over routes and trip start times simultaneously so as to identity start times and routes associated with maximal expected value, or equivalently minimum expected cost, given preferences encoded about one or more of the leaving time, the travel time, and the arrival time.
There is a need to provide simple, accurate, fast and computationally inexpensive methods of object and hand pose recognition for many applications. For example, to enable a user to make use of his or her hands to drive an application either displayed on a tablet screen or projected onto a table top. There is also a need to be able to discriminate accurately between events when a user’s hand or digit touches such a display from events when a user’s hand or digit hovers just above that display. A random decision forest is trained to enable recognition of hand poses and objects and optionally also whether those hand poses are touching or not touching a display surface. The random decision forest uses image features such as appearance, shape and optionally stereo image features. In some cases, the training process is cost aware. The resulting recognition system is operable in real-time.
Loyalty offer techniques are described. In one or more implementations, data is received from a plurality of merchants via a network, the data describing transactions for goods or services initiated at physical locations of respective said merchants and including identifiers that uniquely identify mobile communication devices that were used to initiate the transactions. Information is updated that describes participation in one or more loyalty offers associated with the plurality of merchants using the identifiers that uniquely identify the mobile communication devices and the data that describes the transactions.