Hardware components | ||||||
 |
| × | 1 | |||
 |
| × | 1 | |||
Software apps and online services | ||||||
 |
| |||||
Hand tools and fabrication machines | ||||||
 |
| |||||
According to Chapter. 8., this application is supposed to recognize the words “yes”, “no”, and is also capable of distinguishing between unknown words and silence or background noise. Since there is a built-in microphone, I trained a wake word detection ML model and implemented this application is implemented on the Arduino Nano 33 BLE Sense board.
The application uses a model which was trained on a dataset called the Speech Commands Dataset. This dataset consists of 65, 000 one-second long utterances of 30 short words, crowdsourced online. The application will capture the audio and use the model to distinguish the sound, then take action based on the command it heard.
After loading the application into Arduino IDE and connecting the board to the laptop, I uploaded the application to the board. Then I tested several times and the results show it works. However, this application is kind of naive and sometimes we need to repeat a word several times to make the application hear that.
The test case of "yes":
The test case of "no":
Comments