公开(公告)号：US09111537B1

公开(公告)日：2015-08-18

申请号：US14325002

申请日：2014-07-07

Applicant: Google Inc.

Inventor： Matthew Wiseman ,  Yaniv Bernstein ,  Daniel Switkin ,  Gheorghe M. Postelnicu ,  Matthew Sharifi ,  Annie Chen ,  Dominik Roblek

IPC: H04M11/00 ,  G10L15/22

CPC classification number: G10L15/22 ,  G06F17/30758 ,  G10L15/30 ,  G10L25/54

Abstract: An audio recognition service recognizes an audio sample across multiple content types. At least a partial set of results generated by the service are returned to a client while the audio sample is still being recorded and/or transmitted. The client additionally displays the results in real-time or near real-time to the user. The audio sample can be sent over a first HTTP connection and the results can be returned over a second HTTP connection. The audio recognition service further processes check-in selections received from the client for content items indicated by the results. Responsive to receiving the check-in selections, the service determines whether a user is eligible for a reward. If the user is eligible, the service provides the reward.

Abstract translation: 音频识别服务识别多种内容类型的音频样本。 当音频样本仍然被记录和/或发送时，由服务产生的至少一部分结果返回给客户机。 客户端另外向用户实时或接近实时显示结果。 音频样本可以通过第一个HTTP连接发送，并且可以通过第二个HTTP连接返回结果。 音频识别服务进一步处理从客户端接收的用于由结果指示的内容项的登记选择。 响应于接收签入选择，该服务确定用户是否有资格获得奖励。 如果用户符合条件，则该服务将提供奖励。

公开(公告)号：US08775191B1

公开(公告)日：2014-07-08

申请号：US14078724

申请日：2013-11-13

Applicant: Google Inc.

Inventor： Matthew Sharifi ,  Dominik Roblek ,  Sandeep Siddhartha

IPC: G06F17/27

CPC classification number: G10L15/26 ,  G10L25/21 ,  G10L2015/088

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for classifying utterances. The methods, systems, and apparatus include actions of obtaining an audio input signal representing an utterance of a user. Additional actions may include determining that a shape of at least a portion of the audio input signal matches a shape of at least a portion of an audio trigger signal corresponding to a keyword. Further actions may include, based at least on determining that the shape of at least the portion of the audio input signal matches the shape of at least the portion of an audio trigger signal corresponding to the keyword, classifying the utterance as a trigger utterance that corresponds to the keyword.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于分类话语。 方法，系统和装置包括获得表示用户的话语的音频输入信号的动作。 附加动作可以包括确定音频输入信号的至少一部分的形状与对应于关键字的音频触发信号的至少一部分的形状相匹配。 至少基于确定音频输入信号的至少一部分的形状与对应于关键字的音频触发信号的至少部分的形状相匹配，进一步的动作可以包括：将话语分类为对应的触发话语 关键字