公开(公告)号：US20170075992A1

公开(公告)日：2017-03-16

申请号：US15362185

申请日：2016-11-28

Applicant: Google Inc.

Inventor： Ant Oztaskent ,  Yaroslav Volovich ,  Joanna Chwastowska

IPC: G06F17/30

CPC classification number: G06F17/30746 ,  G06F17/30769 ,  G06F17/30864

Abstract: Systems, methods, and media for identifying content are provided. In some implementations, systems for identifying content are provided, the systems comprising: at least one hardware processor that: receives content having audio; generates a representation of the audio of the content; performs a first database search based on the representation; performs a second database search based on text corresponding to words that are sung or spoken in the content; responsive to determining that the first database search yielded a match and the second database search yielded a match, causes a first indication that the content contains a known performance of known content to be output; and responsive to determining that the first database search failed to yield a match and the second database search yielded a match, causes a second indication that the content contains an unknown performance of known content to be output.

Abstract translation: 提供了用于识别内容的系统，方法和媒体。 在一些实现中，提供了用于识别内容的系统，所述系统包括：至少一个硬件处理器，其接收具有音频的内容; 生成内容的音频的表示; 基于该表示执行第一数据库搜索; 基于对应于在内容中演唱或说出的单词的文本执行第二数据库搜索; 响应于确定所述第一数据库搜索产生匹配并且所述第二数据库搜索产生匹配，导致所述内容包含已知内容的已知性能的第一指示被输出; 并且响应于确定所述第一数据库搜索失败以产生匹配并且所述第二数据库搜索产生匹配，导致所述内容包含已知内容的未知性能的第二指示被输出。

公开(公告)号：US09507860B1

公开(公告)日：2016-11-29

申请号：US13827249

申请日：2013-03-14

Applicant: Google Inc.

Inventor： Ant Oztaskent ,  Yaroslav Volovich ,  Joanna Chwastowska

IPC: G06F17/30 ,  G06F7/00

CPC classification number: G06F17/30746 ,  G06F17/30769 ,  G06F17/30864

Abstract: Systems, methods, and media for identifying content are provided. In some implementations, systems for identifying content are provided, the systems comprising: at least one hardware processor that: receives content having audio; generates a representation of the audio of the content; performs a first database search based on the representation; performs a second database search based on text corresponding to words that are sung or spoken in the content; responsive to determining that the first database search yielded a match and the second database search yielded a match, causes a first indication that the content contains a known performance of known content to be output; and responsive to determining that the first database search failed to yield a match and the second database search yielded a match, causes a second indication that the content contains an unknown performance of known content to be output.

Abstract translation: 提供了用于识别内容的系统，方法和媒体。 在一些实现中，提供用于识别内容的系统，所述系统包括：至少一个硬件处理器，其接收具有音频的内容; 生成内容的音频的表示; 基于该表示执行第一数据库搜索; 基于对应于在内容中演唱或说出的单词的文本执行第二数据库搜索; 响应于确定所述第一数据库搜索产生匹配并且所述第二数据库搜索产生匹配，导致所述内容包含已知内容的已知性能的第一指示被输出; 并且响应于确定所述第一数据库搜索失败以产生匹配并且所述第二数据库搜索产生匹配，导致所述内容包含已知内容的未知性能的第二指示被输出。