Picked up a compact ESP32 recently and wanted to try using it to solve an annoyance of mine. I used the ESP32's camera, a small classification model and Home Assistant to automate muting and unmuting the TV when an ad shows up when I'm watching Prime Video. |
I wonder what's a way to detect ADs just from audio. Maybe by volume?
For audio based detection, I would start with collecting a large corpus of normal shows vs ad segment audio dataset. I assume the amplitude (volume changes) and frequency distribution would be unique enough to distinguish between them.
Train a model using their Mel Spectrogram and deploy on-device.
Microphone -> ADC -> Preprocessing -> Spectrogram Generation -> Inference -> Mute/Unmute
Would be an interesting project.