But your solution costs money in addition to the phone they already own for other purposes. And multiple things can make loud noises in your environment besides babies; differentiating between a police siren going by outside and your baby crying is useful, especially if the baby slept through the siren.

The same arguments were said for blind people and the multitude of one-off devices that smartphones replaced, OCR to TTS, color detection, object detection in photos/camera feeds, detecting what denomination US bills are, analyzing what's on screen semantically vs what was provided as accessible text (if any was at all), etc. Sure, services for the blind would come by and help arrange outfits for people, and audiobook narrators or braille translator services existed, and standalone devices to detect money denominations were sold, but a phone can just do all of that now for much cheaper.

All of these accessibility AI/ML features run on-device, so the knee-jerk anti-AI crowd's chief complaints are mostly baseless anyways. And for the blind and the deaf, carrying all the potential extra devices with you everywhere is burdensome. The smartphone is a minimal and common social and physical burden.

>Is that something you actually need AI for though?

Need? Probably not. I bet it helps though (false positives, etc.)

>would be cheaper, faster detection, more reliable, easier to maintain, and more.

Cheaper than the phone I already own? Easier to maintain than the phone that I don't need to do maintenance on?

From a fun hacking perspective, a different sensor & device is cool. But I don't think it's any of the things you mentioned for the majority of people.