公开(公告)号：US09842608B2

公开(公告)日：2017-12-12

申请号：US14727741

申请日：2015-06-01

Applicant: Google Inc.

Inventor： Raziel Alvarez Guevara ,  Preetum Nakkiran

IPC: G10L21/034 ,  G10L25/78 ,  H03G3/30

CPC classification number: G10L21/034 ,  G10L25/78 ,  H03G3/3005

Abstract: This specification describes, among other things, a computer-implemented method. The method can include receiving a stream of audio data at a computing device. The stream of audio data can be segmented into a plurality of audio segments. Respective intensity levels are determined for each of the plurality of audio segments. For each of the plurality of audio segments and based on the respective intensity levels, a determination can be made as to whether the audio segment includes a speech signal. Selective gain control can be performed on the stream of audio data by automatically adjusting a gain of particular ones of the plurality of audio segments that are determined to include a speech signal.

公开(公告)号：US09767410B1

公开(公告)日：2017-09-19

申请号：US14739335

申请日：2015-06-15

Applicant: Google Inc.

Inventor： Raziel Alvarez Guevara ,  Preetum Nakkiran

IPC: G10L15/16 ,  G06N3/08

CPC classification number: G06N3/08 ,  G10L15/16 ,  G10L2015/088

Abstract: This specification describes, among other things, a computer-implemented method. The method can include training a baseline neural network using a first set of training data. For each node in a subset of interconnected nodes in the baseline neural network, a rank-k approximation of a filter for the node can be computed. A subset of nodes in a rank-constrained neural network can then be initialized with the rank-k approximations of the filters from the baseline neural network. The subset of nodes in the rank-constrained neural network can correspond to the subset of nodes in the baseline neural network. After initializing, the rank-constrained neural network can be trained using a second set of training data while maintaining a rank-k filter topology for the subset of nodes in the rank-constrained neural network.

公开(公告)号：US20160099007A1

公开(公告)日：2016-04-07

申请号：US14727741

申请日：2015-06-01

Applicant: Google Inc.

Inventor： Raziel Alvarez ,  Preetum Nakkiran

IPC: G10L21/034

CPC classification number: G10L21/034 ,  G10L25/78 ,  H03G3/3005

Abstract: This specification describes, among other things, a computer-implemented method. The method can include receiving a stream of audio data at a computing device. The stream of audio data can be segmented into a plurality of audio segments. Respective intensity levels are determined for each of the plurality of audio segments. For each of the plurality of audio segments and based on the respective intensity levels, a determination can be made as to whether the audio segment includes a speech signal. Selective gain control can be performed on the stream of audio data by automatically adjusting a gain of particular ones of the plurality of audio segments that are determined to include a speech signal.

Abstract translation: 本说明书尤其描述了计算机实现的方法。 该方法可以包括在计算设备处接收音频数据流。 音频数据流可以被分割成多个音频段。 针对多个音频片段中的每一个确定相应的强度级别。 对于多个音频片段中的每一个并且基于相应的强度级别，可以确定音频片段是否包括语音信号。 可以通过自动调整被确定为包括语音信号的多个音频片段中的特定音频片段的增益，来对音频数据流执行选择性增益控制。