esp32-s3-eye + sound identification

[gamename]

hi,

I'm working on a project that involves both images and sounds. I have an esp32-s3-eye, so video/image capture + identification is working.

But, how can I do sound (*not* speech) recognition? What libraries are appropriate to use in the esp32-s3-eye? ESP-SR?

I already have a TinyML model I can use. So that part is done.

Remember, I'm doing sound identification/recognition, not speech recognition.

Thanks,
-T