Has anyone else noticed that when a man and a woman are sharing a webcam on a video call, that the noise-filtering algorithms often filter out the woman's voice and pick the man's as the frequencies to highlight because... METAPHOR.
-
...It's might not be that the algorithm is biased against women, but that higher voices (women and children) are more similar to the noises in homes/offices that are being filtered out. Sure it sucks (and could be improved), but I wouldn't assume a testing bias is the cause.
I'm assuming the situation is of a woman and a man without significant additional background noise, as I said. It's not hard to differentiate between a female voice and noise, even if they have similar frequency ranges. If that situation wasn't tested, that's a gap in testing.
-
-
I suspect you (like most people with normal hearing) may be unaware of how much background noise there is. Lights, fridges, traffic, neighbours. Like I say, we're really good at filtering these out normally! There may be a gap, but it could also just be that it's MUCH harder.
-
I've got audio experience, I have a pretty good idea of what background noise levels are and how various microphones pick them up and how it sounds in mono :-)
- Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.