This week I wanted to explore using voice to control the microcontroller via machine learning. Sound is a feature I’m considering implementing into my final project so through this assignment I’ve developed a better understanding of the concept.
As shown in the video below, I was successfully able to turn the blue light on by saying “YES” and the yellow light on by saying “NO”. Since we were given a template to build from, it was actually really simple to add just a few lines of code to control the lights. For my final project, I’d like to control an LED strip (potentially with sound) so it felt like useful practice working on this assignment, especially since I haven’t worked with hardware for quite some time. During this process, I ran into some minor issues with the port that took a majority of my time to troubleshoot, but thankfully I got it resolved by finding a new USB cord. I realized that for my final project, I would want a microphone that is considerably more sensitive, as I found that the built-in microphone required me to speak with a really loud tone. Going forward, I would like to explore how to recognize all sorts of sounds and analyze for hundreds or more words, or maybe take amplitude or volume as a factor. As an example, It would be really cool to play a song and see a series of lights animate based on the type of melody or lyrics in real-time.