公开(公告)号：US11282495B2

公开(公告)日：2022-03-22

申请号：US16712567

申请日：2019-12-12

Applicant: Amazon Technologies, Inc.

Inventor： Hongda Mao ,  George Yu-Chien Lin ,  Sundararajan Srinivasan ,  Chu-Cheng Hsieh

IPC: G10L13/027 ,  G10L13/00 ,  G10L17/04 ,  G10L17/18

Abstract: A first neural network model of a user device processes audio data to extract audio embeddings that represent vocal characteristics of a user of an utterance represented in the audio data. The audio embeddings may then be hashed to remove characteristics specific to the user while still maintaining a unique set of characteristics. The hashed embeddings may be sent to a remote system, which may use them to identify the user.

公开(公告)号：US20210183358A1

公开(公告)日：2021-06-17

申请号：US16712567

申请日：2019-12-12

Applicant: Amazon Technologies, Inc.

Inventor： Hongda Mao ,  George Yu-Chien Lin ,  Sundararajan Srinivasan ,  Chu-Cheng Hsieh

IPC: G10L13/027 ,  G10L13/04 ,  G10L17/04 ,  G10L17/18

Abstract: A first neural network model of a user device processes audio data to extract audio embeddings that represent vocal characteristics of a user of an utterance represented in the audio data. The audio embeddings may then be hashed to remove characteristics specific to the user while still maintaining a unique set of characteristics. The hashed embeddings may be sent to a remote system, which may use them to identify the user.