Amazon Technologies, Inc.

Invensense, Inc.

David William Devries

Leo Benedict Baldwin

Omar Sze Leung

Amit Singh Chhetri

Noam Sorek

Serkan Hatipoglu

Michael Devyver

Stewart Robin Shearer

Rajesh Mittal

Derek Keith Shaeffer

David C Buuck

Erik E Anderson

David Sachs

Stephen Lloyd

Nathan Royer

Doug Vargha

Kerry Keal

Jung Bae Sohn

Steve Gil Gonzalez

Ali Shahrokni

Elizabeth Helminski

Techniques for dynamically maintaining speech processing data on a local device for frequently input commands are described. One or more devices receive speech processing data specific to one or more commands associated with system input frequencies satisfying an input frequency threshold. The device(s) then receives input audio corresponding to an utterance and generate input audio data corresponding thereto. The device(s) performs speech recognition processing on input audio data to generate input text data using a portion of the received speech processing data. The device(s) determines a probability score associated with the input text data and determines the probability score satisfies a threshold probability score. The device(s) then performs natural language processing on the input text data to determine the command using a portion of the speech processing data. The device(s) then outputs audio data responsive to the command.

Dynamic speech processing

Techniques for dynamically maintaining speech processing data on a local device for frequently input commands are described. A system determines a usage history associated with a user profile. The usage history represents at least a first command. The system determines the first command is associated with an input frequency that satisfies an input frequently threshold. The system also determines the first command is missing from first speech processing data stored by a device associated with the user profile. The system then generates second speech processing data specific to the first command and sends the second speech processing data to the device.

A system includes a fit test fixture. A first air bladder is connected to the support structure, and a second air bladder is connected to the support structure. The system includes a scanner configured to generate a three-dimensional model of a clothing item positioned over at least a portion of the fit test fixture, and a controller. The controller is configured to cause an air compressor to inflate the first air bladder and the second air bladder, and store the three-dimensional model of the clothing item in a database. The three-dimensional model depicts the clothing item at least partially inhabited by the first air bladder and the second air bladder. A processor is configured to generate a rendering depicting the three-dimensional model of the clothing item on a three-dimensional model of the consumer.

Clothing item measurement and visualization system

A decision engine executing on an electronic device may determine, using sensor data captured by multiple sensors of the device, whether a user is present in an environment that includes the device. If the user is determined to be present in the environment, the device may transition from a first state to a second state. The first state may be a first power state of the device in which the device is powered off or an idle or dormant state in which the device is powered on but a display of the device is powered off. Correspondingly, the second state may be a second power state of the device in which the device and the display are powered on and content is being rendered on the display. If the decision engine cannot make a determination based on the sensor data, a context engine may adjudicate the user presence determination.

Determining a device state based on user presence detection

A system for determining and correcting a calculated orientation of a computing device based on data from an accelerometer and a gyroscope. The system compares a predicted direction of gravity in a predicted frame of the device with a measured direction of gravity in a sensor frame of the device, and determines an angle of the difference between the directions. A correction is calculated to rotate the predicted frame around an axis by the angle relative to a sensor frame, the axis being perpendicular to both the predicted and measured directions of gravity. A predicted orientation of a reference 'Earth' frame relative to the predicted frame is calculated based on the gyroscope data. A corrected orientation is determined by applying the correction to the predicted orientation, providing an orientation of the Earth reference frame relative to the sensor frame.

Inertial sensor fusion orientation correction

The present invention relates to a combination of a 6-axis motion sensor having a 3-axis gyroscope and a 3-axis linear accelerometer, a motion processor and a radio integrated circuit chip (IC), wherein the intelligence in the motion processor enables the communication between the motion sensor, the radio IC and the external network. The motion processor also enables power savings by adaptively controlling the data rate of the motion sensor, depending on the amount or speed of the motion activity.

Wireless motion processing sensor systems suitable for mobile and battery operation

Growing community of inventors

San Jose, CA, United States of America

David William Devries