Speech Activated Audio Attenuation

Inspiration

Our teammate Marcus can't hear other people when he has his earbuds in, so our program solves that problem by lowering his volume when we call his name.

What it does

When the program hears the user's name, it lowers or mutes the volume depending on the user's choice. It also can open the Spotify web player through voice command, as well as closes or resume on command. It also uses text-to-speech for some commands (e.g. to let you know someone is calling your name).

How we built it

We built it in Python using Git and Visual Studio Code. We used the SpeechRecognition, PyAudio, pywin32, PyCaw, and PyTTSX3 libraries.

Challenges we ran into

We're relatively new to using VSCode and downloading Python libraries, so figuring out which libraries to use, how to install them, and use them things properly was a challenge. Getting the voice recognition to work smoothly was a challenge as well.

Accomplishments that we're proud of

We learned how to use Python libraries and got voice commands working!

What we learned

We learned how to install Python libraries.

What's next for Speech Activated Audio Attenuation

If we had more time, we would have liked to learn how to use PocketSphinx's voice recognition, which works offline and is faster than Google's voice recognition. This would make the program more responsive. We also would learn how to make the program interact directly with Windows 10's media player functions (as of now, the program plays and pauses by simulating keypresses, though it does directly affect system volume). We could also add more voice commands.

Built With

• git
• google-web-speech-api
• pyaudio
• pycaw
• python
• pywin32
• visual-studio