Conrad Irwin wrote: >> Just as with image captchas, you'd need to introduce noise into it. >> > If you are working from known constituents, you can use > cross-correlation to ignore noise pretty effectively (I believe it's > what humans do). The choice then is either to make the noise sound > like the captcha's numbers (google's approach), which is very hard to > solve (at least I find it so), or to use ReCAPTCHAs
Funny. It turns out that now Recaptcha belong to Google. > vast database of > unknown sound files (with noise added to obscure the phonemes). The > human brain is capable of filling in completely obscured phonemes in > order to make the sentence "make sense" I wonder if we could abuse Wikimania presentations audio asking to write each word from it. >(assuming they speak the > language in question - another usability problem with these), Certainly. That's a very big drawback on adding audio captchas to WMF prjects. > It's likely to be much easier to improve the "request an account from > a human" process - which has inbuilt rate-limiting, a little bit of > turing test, and a nice splash of common sense that is so hard to > instill in an automated system. That would be removing the "Completely Automated" part :) It's not a bad idea, but what should we ask them? A too open textarea leads to "Plz make an account" reasons which have very little Turing entropy. "Please summarise the Main Page featured article so we know that you have a decent brain" would be more secure, but our users wouldn't be too happy with that. >> I have been trying flite, and didn't find the synthesized text too >> understable by itself. :( >> > > In which case a computer could probably solve them better than you :). Surely. I suspect that would be quite easy to crack by comparing with each phonema. :) _______________________________________________ Wikitech-l mailing list Wikitech-l@lists.wikimedia.org https://lists.wikimedia.org/mailman/listinfo/wikitech-l
