Edge computing IoT Device for Voice processing

[YSN]

I would like to build edge computing IoT Device for voice commands recognition. (In short Speech Recognition at edge).

What is best suitable STM32 device with digital microphone and speaker interface (similar to echodot or google home, where processing is at clould, but HW should be same ?).

What is the starting point for implementation, like AI & ML on STM32 or any other approach ?

[Miguel CASTRO]

Did you had a look to this page?

https://www.st.com/content/st_com/en/ecosystems/stm32-alexa-voice.html