公开(公告)号：US09728188B1

公开(公告)日：2017-08-08

申请号：US15195587

申请日：2016-06-28

Applicant: Amazon Technologies, Inc.

Inventor： Alexander David Rosen ,  Michael James Rodehorst ,  George Jay Tucker ,  Aaron Lee Mathers Challenner

IPC: G10L15/22 ,  G10L15/08 ,  G10L25/51 ,  G10L15/28 ,  G10L19/08

CPC classification number: G10L15/22 ,  G10L19/08 ,  G10L25/18 ,  G10L25/51 ,  G10L2015/223

Abstract: Systems and methods for detecting similar audio being received by separate voice activated electronic devices, and ignoring those commands, is described herein. In some embodiments, a voice activated electronic device may be activated by a wakeword that is output by the additional electronic device, such as a television or radio, may capture audio of sound subsequently following the wakeword, and may send audio data representing the sound to a backend system. Upon receipt, the backend system may, in parallel to performing automated speech recognition processing to the audio data, generate a sound profile of the audio data, and may compare that sound profile to sound profiles of recently received audio data and/or flagged sound profiles. If the generated sound profile is determined to match another sound profiles, then the automated speech recognition processing may be stopped, and the voice activated electronic device may be instructed to return to a keyword spotting mode. If the matching sound profile is not already stored in a database of known sound profiles, it can be stored for future comparisons.

公开(公告)号：US10515312B1

公开(公告)日：2019-12-24

申请号：US14984847

申请日：2015-12-30

Applicant: Amazon Technologies, Inc.

Inventor： Yotaro Kubo ,  George Jay Tucker

IPC: G06N7/00 ,  G06N3/08

Abstract: The present disclosure is directed to the generation of a compact artificial neural network by removing individual nodes from the artificial neural network. Individual nodes of the artificial neural network may be deactivated randomly and/or selectively during training of the artificial neural network. In some embodiments, a particular node may be randomly deactivated approximately half of the time during processing of a set of training data inputs. Based on the accuracy of the results obtained when the node is deactivated compared to the accuracy of the results obtained when the node is activated, an activation probability may be generated. Nodes can then be selectively removed from the artificial neural network based on the activation probability.