TensorFlow Lite: Micro Speech

Getting started with TensorFlow Lite: Micro Speech

AMB21 / AMB22 Wiring Diagram:

Connect the microphone and LEDs to the RTL8722 board following the diagram.

AMB23 Wiring Diagram:

As RTL8722DM MINI have a built in microphone on the board, there is no need for any external microphone. For the LEDs, we will only connect two LEDs and then use the two onboard LEDs (Blue and Green).

1. Download the Ameba customized version of TensorFlow Lite for Microcontrollers library at https://github.com/ambiot/ambd_arduino/tree/master/Arduino_zip_libraries.

2. Follow the instructions at https://www.arduino.cc/en/guide/libraries to install it.

3. Ensure that the patch files found at https://github.com/ambiot/ambd_arduino/tree/master/Ameba_misc/ are also installed.

Open the example, “Files” -> “Examples” -> “TensorFlowLite_Ameba” -> “micro_speech”.

Upload the code and press the reset button on Ameba once the upload is finished. Once it is running, you should see one of the LEDs flashing, indicating that it is processing audio. Saying the word “yes” will cause the green LED to light up. Saying the word “no” will cause the red LED to light up. If the word is not recognized, the blue LED will to light up.

The inference results are also output to the Arduino serial monitor, which appear as follows:

If you are having trouble in getting the words recognized, here are some tips:– Ensure that your surroundings are quiet with minimal noise.– Experiment with varying the distance of the microphone, starting with it at an arm’s length.– Experiment with different tones and volume when saying the words.– Depending on how you pronounce the words, the characteristics of the microphone used, getting one keyword recognized may be easier than the other.

Code Reference

More information on TensorFlow Lite for Microcontrollers can be found at: https://www.tensorflow.org/lite/microcontrollers

More resources:

For more information on the example: https://www.amebaiot.com/en/amebad-arduino-audio-tensorflow-microspeech/

If you are interested to know more about Ameba, do visit the Ameba official website or join the Facebook page or Forum for more discussion!

• Ameba Official Website: https://www.amebaiot.com/en/
• Ameba Facebook Group: https://www.facebook.com/groups/amebaioten
• Ameba Forum: https://forum.amebaiot.com/
• Instagram: https://www.instagram.com/amebaiotcrab/