Wake word detection configuration

#Electronic devices, such as mobile phones, typically rely on tactile inputs such as touchscreen inputs and/or button actuations to perform operations. Additional input means may be desired. Described herein are improvements in technology and solutions to technical problems that can be used to, among other things, increase the availability of non-tactile input means for electronic device users.

#The detailed description is set forth below with reference to the accompanying figures. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The use of the same reference numbers in different figures indicates similar or identical items. The systems depicted in the accompanying figures are not to scale and components within the figures may be depicted not to scale with each other.

#FIG. 1 illustrates a schematic diagram of an example environment for wake word detection configuration.

#FIG. 2 illustrates a conceptual diagram of components of an electronic device having stored in memory one or more applications for wake word detection configuration.

#Systems and methods for wake word detection configuration are described herein. Take, for example, an electronic device, such as a mobile phone, that includes components that facilitate the detection of wake words from user utterances. The electronic device may include a microphone that may be configured to capture audio representing the user utterance and generate corresponding audio data. The electronic device may also include a digital signal processor and a digital-signal-processor component configured to cause the digital signal processor to detect a wake word in the audio data. The electronic device may also have stored thereon one or more wake word application programming interfaces (APIs) that are associated with a remote speech-processing system. When the digital signal processor, using the digital-signal-processor component, detects the wake word, an indication that the wake word has been detected may be sent to the wake word APIs along with the audio data.

#The wake word APIs may determine whether a speech-processing application associated with the remote speech-processing system has been installed on the electronic device. To illustrate, in examples, the electronic device, and/or portions thereof, may be manufactured and pre-programmed to include the digital-signal-processor component and the wake word APIs. These applications may be considered “privileged” or otherwise may be separated from “non-privileged” applications and/or memory. However, the speech-processing application may not be pre-programmed into memory of the electronic device. As such, the wake word APIs may, based at least in part on receiving an indication that a user utterance includes the wake word, determine whether the speech-processing application has been installed.

#In examples where the speech-processing application has not been installed, the wake word APIs, and/or one or more other components of the electronic device, may be configured to cause a display of the electronic device to display a selectable link and/or another form of a request for a user of the electronic device to install the speech-processing application, such as from an application store available to the electronic device. A user may provide an input selecting the link, which may cause the application store to open and display one or more options for installing the speech-processing application. In these examples where the speech-processing application has not been installed, the audio data provided at the digital-signal processing application may be deleted or otherwise removed from a buffer of audio data. The user may provide input for initiating installation of the speech-processing application.