Starting with the Windows IoT Core 14986 release, Microsoft has added the Cortana voice assistant feature. Before, we could only use local speech recognition, and we needed to write the application to download it to the device. From now on, Microsoft has integrated the Cortana voice assistant from the system level, enabling users to start Cortana and interact with Cortana in real time with system settings. Let's try the process of using Cortana as a Windows IoT core device with Raspberry Pi.
1. Hardware Preparation
- Raspberry Pi 2/Raspberry Pi 3, 5v/2a power supply, TF card (above 8GB)
- Microphone: Microsoft LifeCam HD 3000 (the camera is integrated with a microphone), or you can use other microphones, such as blue Snowball ICE condenser microphone, cardioid, sound Tech CM-100 0USB Table Top Conference Meeting Microphone
- Audio output device: The Raspberry Pi of the Windows IoT core system only supports the audio output of the 3.5mm interface, and HDMI audio output is not supported. So, you can connect to a normal 3.5mm interface headset.
- Display device: A monitor that can connect to the HDMI interface, or a monitor that transfers the VGA interface using the active HDMI to VGA module.
2. Software Settings
Write the Windows IoT Core system image for Raspberry Pi, note that the version is more than 14986, preferably the latest version 15026. Insert the system-burning TF card into the Raspberry Pi, connect the power supply, monitor, insert the Microsoft LIFECAM HD 3000 USB interface into the Raspberry Pi USB port, and then power on to start the Windows IoT Core system.
2.1 Cortana settings for Raspberry Pi
After the system starts, using the mouse, click the Settings button on the interface, go to the Settings screen, select Cortana in it, and turn it on, as shown in.
Click on the "About Me" button below and sign in with your Microsoft account to make Cortana's settings, as shown in.
On the Change my Name page, the user can enter a name, and the system displays Cortana's help information, as shown in.
On the Favorite Places page, users can enter home, work, or other places to keep Cortana in mind. As shown in.
For this step, if the user does not want to plug in the mouse keyboard on the Raspberry Pi, you can also search the Windows IoT Remote Client tool in the store store, and after installing locally, remotely connect the Raspberry Pi, which is done locally.
2.2 Settings for Windows Device Portal
Users can use the browser to log on to the device's Windows devices Portal to make relevant settings. The method is as follows, first, open the browser, enter the device's IP address and 8080 port, enter the current user name and password in the authentication page that pops up (the system defaults to administrator/[email protected]). Position it on the Device Setting page, select the Cortana option below, and adjust the volume of speaker and microphone to 40-70, note that microphone is not set to 0. As shown in.
Once you've set it up, you can restart your device to use Cortana.
3. Cortana's use
After the system starts, you can see if Cortana has started with Settings-app Manager in Windows Device Portal, as shown in.
At this point, the user can wake Cortana directly using "Hey,cortana", as shown in the device interface.
The user can interact with Cortana. For example, ask about the weather and Cortana will give you a local weather condition. As shown in.
By default, if a user stops interacting with Cortana, after about 10 seconds, Cortana will automatically go to the background.
4. Precautions
1. Used on Raspberry Pi, Cortana's animations are not good due to GPU-driven reasons. But using Cortana on Minnowboard Max does not have this problem.
2. Chinese voice interaction is not supported at this time and should be added later.
3. For the microphone hardware, you can use some USB sound card to replace, but recommended to use the hardware given above, because the above hardware is officially tested by Microsoft, compatibility is better.
Windows IoT Serials 4-How to use Cortana voice assistant on a Raspberry Pi