Kernel Shape in a CNN Audio Model

Thu, 15 May 2025 12:27:54 -0700

(Code on GitHub.)

Audio has a strong temporal component. Unlike an image, audio is a thing that happens in time, not an arrangement of items in a space. And yet many audio classification models treat spectrograms as if they were still images and not events, an artifact of early successes applying visual models to audio datasets.

I took the ESC-50 dataset, created a simple five-layer CNN model, and trained it with various kernel shapes and sizes. My hypothesis: kernels that extend more in the temporal dimension will have better performance.

Audio on This Might Be Something!

Kernel Shape in a CNN Audio Model