Detecting a trigger of a digital assistant

Abstract

Systems and processes for operating an intelligent automated assistant are provided. In accordance with one example, a method includes, at an electronic device with one or more processors, memory, anda plurality of microphones, sampling, at each of the plurality of microphones of the electronic device, an audio signal to obtain a plurality of audio signals; processing the plurality of audio signals to obtain a plurality of audio streams; and determining, based on the plurality of audio streams, whether any of the plurality of audio signals corresponds to a spoken trigger. The method further includes, in accordance with a determination that the plurality of audio signals corresponds to the spoken trigger, initiating a session of the digital assistant; and in accordance with a determinationthat the plurality of audio signals does not correspond to the spoken trigger, foregoing initiating a session of the digital assistant.

Description

[0001] This application claims priority from the following patent applications: U.S. Provisional Patent Application No. 62 / 507,042, entitled "DETECTING A TRIGGER OF A DIGITAL ASSISTANT," filed May 16, 2017; Danish Patent Application No.PA201770420, titled "DETECTING A TRIGGER OF A DIGITAL ASSISTANT", filed May 31, 2017; and Danish Patent Application No. PA201770421, titled "DETECTING A TRIGGER OF A DIGITAL ASSISTANT" Triggering of Digital Assistants), submitted May 31, 2017. The content of the above patent application is hereby incorporated by reference in its entirety. technical field [0002] The present invention relates generally to intelligent automated assistants, and more particularly to detecting triggers of digital assistants. Background technique [0003] Intelligent automated assistants (or digital assistants) can provide a favorable interface between human users and electronic devices. Such assistants may allow users to interact with a device or system using na...

AI Technical Summary

Problems solved by technology

However, the sampled audio signal may include interfering audio signals, such as speech from competing speakers (e.g., people other than the user who is physically close to the electronic device), audio output from noise sources (e.g., a television in a room), mixed ring

As a result, the electronic device may fail to detect a voice trigger from the user due to interfering noise, or may falsely detect a voice trigger from an interfering audio signal (e.g., mistaking "History" from a competing speaker for "Hey Siri (Hi Siri)")

In addition, the electronic device may not be able to distinguish between portions of the sampled audio signal intended for the digital assistant and portions of the sampled audio signal not intended for the digital assistant (e.g., a conversation between two speakers)

This, in turn, leads to a confusing and inefficient user experience, as the electronic device may initiate a digital assistant session when the user does not issue a voice trigger, fail to initiate a digital assistant session when the user issues a voice trigger, and / or misinterpret user requests to the digital assistant

Images