公开(公告)号：US09953637B1

公开(公告)日：2018-04-24

申请号：US14225135

申请日：2014-03-25

Applicant: Amazon Technologies, Inc.

Inventor： Giuseppe Di Fabbrizio ,  Wei Chen ,  Benjamin Edward Lambert

IPC: G10L15/00 ,  G10L15/04 ,  G10L15/08

CPC classification number: G10L15/22 ,  G10L15/1815

Abstract: Features are disclosed for processing user utterances and applying user-supplied corrections to future user utterances. If a user utterance is determined to relate to a speech processing error that occurred when processing a previous utterance, information about the error or a correction thereto may be stored. Such information may be referred to as correction information. Illustratively, the correction information may be stored in a skip list. Subsequent utterances may be processed based at least partly on the correction information. For example, speech processing results generated from processing subsequent utterances that include a term associated with the error may be removed or re-scored in order to reduce or prevent the chance that an error will be repeated.

公开(公告)号：US10368057B1

公开(公告)日：2019-07-30

申请号：US15279212

申请日：2016-09-28

Applicant: Amazon Technologies, Inc.

Inventor： Sajesh Kumar Saran ,  Brad Nathaniel Arnold ,  Jack G Song ,  Tyler Ogren Vrooman ,  Wei Chen ,  Todd Nelson Schoepflin

IPC: H04N13/296 ,  G11B27/10 ,  H04N9/04 ,  H04N5/12 ,  H04N13/257 ,  H04N13/275

Abstract: This disclosure describes techniques for synchronizing independent data streams. In some instances, a computing device couples to multiple independent sensors, such as cameras, and applies accurate timestamp information to the individual frames of sensor data from the independent sensors. After aligning these data streams by applying these accurate timestamps, the computing device may, in some instances, encode and transmit these timestamped data streams to one or more entities for further processing. In one example, a first camera (e.g., a depth camera configured to generate a depth map) may capture images of an environment, as may a second camera (e.g., an Red-Green-Blue (RGB) camera configured to generate color images). The resulting images may be temporally aligned with one another via the timestamping, and the resulting aligned images from both the depth sensor and the RGB camera may be used to create a three-dimensional (3D) model of the environment.

公开(公告)号：US10140581B1

公开(公告)日：2018-11-27

申请号：US14580059

申请日：2014-12-22

Applicant: Amazon Technologies, Inc.

Inventor： Imre Attila Kiss ,  Wei Chen ,  Anjishnu Kumar

IPC: G06N99/00 ,  G06N7/00

Abstract: Features are disclosed for generating models, such as conditional random field (“CRF”) models, that consume less storage space and/or transmission bandwidth than conventional models. In some embodiments, the generated CRF models are composed of fewer or alternate components in comparison with conventional CRF models. For example, a system generating such CRF models may forgo the use of large dictionaries or other cross-reference lists that map information extracted from input (e.g., “features”) to model parameters; reduce in weight (or exclude altogether) certain model parameters that may not have a significant effect on model accuracy; and/or reduce the numerical precision of model parameters.