公开(公告)号：US20160293167A1

公开(公告)日：2016-10-06

申请号：US15179717

申请日：2016-06-10

Applicant: Google Inc.

Inventor： Yu-hsin Joyce Chen ,  Ignacio Lopez Moreno ,  Tara N. Sainath ,  Maria Carolina Parada San Martin

IPC: G10L17/18 ,  G10L17/22 ,  G10L17/08

CPC classification number: G10L17/18 ,  G06N3/0454 ,  G10L17/08 ,  G10L17/22 ,  H04N21/23406 ,  H04N21/23476 ,  Y10S707/99953

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing speaker verification. In one aspect, a method includes accessing a neural network having an input layer that provides inputs to a first hidden layer whose nodes are respectively connected to only a proper subset of the inputs from the input layer. Speech data that corresponds to a particular utterance may be provided as input to the input layer of the neural network. A representation of activations that occur in response to the speech data at a particular layer of the neural network that was configured as a hidden layer during training of the neural network may be generated. A determination of whether the particular utterance was likely spoken by a particular speaker may be made based at least on the generated representation. An indication of whether the particular utterance was likely spoken by the particular speaker may be provided.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的用于执行说话者验证的计算机程序。 一方面，一种方法包括访问具有输入层的神经网络，所述输入层向第一隐藏层提供输入，所述第一隐藏层的节点仅分别连接到来自输入层的输入的适当子集。 可以将对应于特定话语的语音数据提供给神经网络的输入层的输入。 可以生成在神经网络的训练期间被配置为隐藏层的神经网络的特定层响应于语音数据而发生的激活的表示。 可以至少基于所生成的表示来确定特定说话者是否可能说出特定话语的确定。 可以提供特定说话者是否可能说出特定话语的指示。

公开(公告)号：US20160217367A1

公开(公告)日：2016-07-28

申请号：US14613493

申请日：2015-02-04

Applicant: Google Inc.

Inventor： Ignacio Lopez Moreno ,  Yu-hsin Joyce Chen

IPC: G06N3/08 ,  G06N7/00 ,  G06F17/16 ,  G10L15/16

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. One of the methods includes generating, by a speech recognition system, a matrix from a predetermined quantity of vectors that each represent input for a layer of a neural network, generating a plurality of sub-matrices from the matrix, using, for each of the sub-matrices, the respective sub-matrix as input to a node in the layer of the neural network to determine whether an utterance encoded in an audio signal comprises a keyword for which the neural network is trained.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的用于训练神经网络的计算机程序。 方法之一包括通过语音识别系统从预定量的向量生成矩阵，每个向量表示神经网络的层的输入，从矩阵生成多个子矩阵，对于每个 子矩阵，相应的子矩阵作为对神经网络层中的节点的输入，以确定在音频信号中编码的话语是否包括训练神经网络的关键字。