公开(公告)号：US11205420B1

公开(公告)日：2021-12-21

申请号：US16436562

申请日：2019-06-10

Applicant: Amazon Technologies, Inc.

Inventor： Gengshen Fu ,  Thibaud Senechal ,  Shiv Naga Prasad Vitaladevuni ,  Michael J. Rodehorst ,  Varun K. Nagaraja

IPC: G10L15/16 ,  G10L15/22 ,  G10L15/06 ,  G06N3/04 ,  G06N3/02 ,  G10L25/30 ,  G10L15/08

Abstract: A system and method performs wakeword detection using a neural network model that includes a recurrent neural network (RNN) for processing variable-length wakewords. To prevent the model from being influenced by non-wakeword speech, multiple instances of the model are created to process audio data, and each instance is configured to use weights determined by training data. The model may instead or in addition be used to process the audio data only when a likelihood that the audio data corresponds to the wakeword is greater than a threshold. The model may process the audio data as represented by groups of acoustic feature vectors; computations for feature vectors common to different groups may be re-used.