公开(公告)号：US20160343377A1

公开(公告)日：2016-11-24

申请号：US14977494

申请日：2015-12-21

Applicant: Apple Inc.

Inventor： Jerome R. BELLEGARDA ,  Kim E.A. SILVERMAN

IPC: G10L17/22 ,  G10L17/04 ,  G10L17/08 ,  G10L17/14

CPC classification number: G10L17/22 ,  G10L15/07 ,  G10L17/04 ,  G10L17/08 ,  G10L17/14

Abstract: A method and system for training a user authentication by voice signal are described. In one embodiment, a set of feature vectors are decomposed into speaker specific recognition units. The speaker-specific recognition units are used to compute distribution values to train the voice signal. In addition, spectral feature vectors are decomposed into speaker-specific characteristic units which are compared to the speaker-specific distribution values. If the speaker-specific characteristic units are within a threshold limit of the speaker-specific distribution values, the speech signal is authenticated.

Abstract translation: 描述了通过语音信号训练用户认证的方法和系统。 在一个实施例中，一组特征向量被分解成说话者特定识别单元。 扬声器特定识别单元用于计算分配值以训练语音信号。 此外，频谱特征向量被分解成与特定于扬声器的分布值相比较的扬声器特定特征单元。 如果扬声器特有特征单元在扬声器特定分布值的阈值限度内，则认证语音信号。