Implementing Voice Recognition on the i.MX 8M Plus Development Board

[dpcivl]

I am a beginner developer currently using the i.MX 8M Plus development board and I'm interested in implementing voice recognition features. In my research, I came across something called Voice Intelligent Technology (VIT) and I am looking to create a model that supports the Korean language. However, I am unsure of the process, especially when it comes to using header files.

1. From what I've found, it seems that I need to use the SDK in MCUXpresso IDE, but I've failed in applying the archive file.
2. I have a header file containing model information, but I suspect that's not enough for it to work. I would like to know what additional files I need to prepare.
3. I confirmed that VIT-related technologies can be applied through the MPU of the i.MX 8M Plus, but it seemed that MCUXpresso IDE supports only the RT series models. Could you provide me with a rough procedure on how to create a voice recognition program on the i.MX 8M Plus?

Thank you.

[Zhiming_Liu · Accepted solution]

Hi @dpcivl 

When you choose SDK library, you need choose VoiceSpot and VoiceSeeker.

For VIT User Guide, you can find it in below website

https://www.nxp.com/design/design-center/software/embedded-software/voice-intelligent-technology-wak...

For VIT on i.MX8MPlus, please refer below website and download Low Power Voice UI Demo.pdf

https://www.nxp.com/design/design-center/software/embedded-software/application-software-packs/appli...

You need to use 8MIC board to test the Low Power Voice UI Demo.

You can run the demo firstly, and then modify it to realize your model and functions.

Best Regards

Zhiming

[Zhiming_Liu]

Hi @dpcivl 

Which core you want to apply VIT, M7 or A53?

[dpcivl]

I want to apply to M7.