公开(公告)号：US09595264B2

公开(公告)日：2017-03-14

申请号：US14506955

申请日：2014-10-06

Applicant: Avaya Inc.

Inventor： John Jacob ,  Keith Ponting ,  Wendy J. Holmes

IPC: G06F17/27 ,  G06F17/28 ,  G10L19/00 ,  G10L25/51 ,  G10L15/08 ,  H04M3/493

CPC classification number: G10L19/00 ,  G10L15/08 ,  G10L25/51 ,  H04M3/4936

Abstract: To detect events in an audio stream, frames of an audio signal (e.g., frames generated by a codec for a voice call or music stream) are received. Based on information in the frames, an index is used to look up an entry in a table associated with the codec. Each entry in the table indicates a likelihood that a frame matches a sound model element. The likelihood is used in the search for a sound bite, word, and/or phrase in the audio signal. The process of dynamic programming is used to find the combined likelihood for a match of the word, phrase, and/or sound bite to a region of the audio stream. Upon detection of the word, phrase, and/or sound bite in the audio stream, an event is generated, such as, notifying a person or logging the event in a database.

Abstract translation: 为了检测音频流中的事件，接收音频信号的帧（例如，用于语音呼叫或音乐流的编解码器产生的帧）。 基于帧中的信息，使用索引来查找与编解码器相关联的表中的条目。 表中的每个条目表示帧与声音模型元素匹配的可能性。 可能性用于在音频信号中搜索声音咬合，单词和/或短语。 使用动态编程的过程来找到词，短语和/或声音咬合到音频流的区域的组合似然性。 当检测到音频流中的单词，短语和/或声音咬合时，生成事件，例如通知人或将数据记录在数据库中。

公开(公告)号：US20160098999A1

公开(公告)日：2016-04-07

申请号：US14506955

申请日：2014-10-06

Applicant: Avaya Inc.

Inventor： John Jacob ,  Keith Ponting ,  Wendy J. Holmes

IPC: G10L19/00

CPC classification number: G10L19/00 ,  G10L15/08 ,  G10L25/51 ,  H04M3/4936

Abstract: To detect events in an audio stream, frames of an audio signal (e.g., frames generated by a codec for a voice call or music stream) are received. Based on information in the frames, an index is used to look up an entry in a table associated with the codec. Each entry in the table indicates a likelihood that a frame matches a sound model element. The likelihood is used in the search for a sound bite, word, and/or phrase in the audio signal. The process of dynamic programming is used to find the combined likelihood for a match of the word, phrase, and/or sound bite to a region of the audio stream. Upon detection of the word, phrase, and/or sound bite in the audio stream, an event is generated, such as, notifying a person or logging the event in a database.

Abstract translation: 为了检测音频流中的事件，接收音频信号的帧（例如，用于语音呼叫或音乐流的编解码器产生的帧）。 基于帧中的信息，使用索引来查找与编解码器相关联的表中的条目。 表中的每个条目表示帧与声音模型元素匹配的可能性。 可能性用于在音频信号中搜索声音咬合，单词和/或短语。 使用动态编程的过程来找到词，短语和/或声音咬合到音频流的区域的组合似然性。 当检测到音频流中的单词，短语和/或声音咬合时，生成事件，例如通知人或将数据记录在数据库中。