公开(公告)号：EP3493202B1

公开(公告)日：2020-07-22

申请号：EP19150939.7

申请日：2018-05-16

Applicant: Apple Inc.

Inventor： KIM, Yoon ,  SRISUWANANUKORN, Charles ,  CARSON, David A. ,  GRUBER, Thomas R. ,  BINDER, Justin G.

IPC: G10L15/30 ,  G10L15/22 ,  G06F3/16 ,  G06F21/32

公开(公告)号：EP3443556A1

公开(公告)日：2019-02-20

申请号：EP18724082.5

申请日：2018-04-25

Applicant: Apple Inc.

Inventor： KIM, Yoon ,  BRIDLE, John ,  ATKINS, Joshua D. ,  LI, Feipeng ,  SOUDEN, Mehrez

IPC: G10L15/22 ,  G10L15/30 ,  G10L21/0216 ,  H04R3/00 ,  G10L25/51 ,  G10L15/18

公开(公告)号：EP3192072A1

公开(公告)日：2017-07-19

申请号：EP15762859.5

申请日：2015-08-27

Applicant: Apple Inc.

Inventor： KIM, Yoon ,  GRUBER, Thomas, R. ,  BRIDLE, John

IPC: G10L15/20

Abstract: Systems and processes are disclosed for dynamically adjusting a speech trigger threshold, which can be used in triggering a virtual assistant. Audio input can be received via a microphone. The received audio input can be sampled, and a confidence level can be determined of whether the sampled audio input includes a portion of a spoken trigger. In response to the confidence level exceeding a threshold, a virtual assistant can be triggered to receive a user command from the audio input. The threshold can be dynamically adjusted in response to perceived events (e.g., events indicating a user may be more or less likely to initiate speech interactions, events indicating a trigger may be difficult to detect, events indicating a trigger was missed, etc.), thereby minimizing both missed triggers and false positive triggering events.

Abstract translation: 公开了用于动态调整语音触发阈值的系统和过程，其可以用于触发虚拟助理。 音频输入可以通过麦克风接收。 可以对接收到的音频输入进行采样，并且可以确定采样的音频输入是否包括口头触发的一部分的置信度。 响应于置信水平超过阈值，可以触发虚拟助理从音频输入接收用户命令。 响应于感知事件可以动态地调整阈值（例如，指示用户可能或多或少地发起语音交互的事件，指示触发可能难以检测的事件，指示触发被错过的事件等）， 从而最小化错过的触发和误报触发事件。