Initial Release of Mozilla’s Open Source Speech Recognition Model and Voice Data

Re:Initial Release of Mozilla’s Open Source Speech Recogniti... by tardygrad on Wednesday November 29, 2017 @09:05PM (#15812848)

This is tangential, but I wonder if something like this could be (mis)used to break captcha - by feeding in the disabled-friendly audio captcha and passing the results back to the captcha server.

As voice recognition becomes more sophisticated I think captchas are going to have to evolve to kjeep up as well.

[ Parent | on HN ]

Re:Initial Release of Mozilla’s Open Source Speech Recogniti... by candiodari on Thursday November 30, 2017 @05:40AM (#15814795)

Captchas are utterly beat, and more so, it's not the technology or difficulty : they are a lost cause. Pretty much any problem you might present in a captcha, machine learning performs better than humans.

So today, failure to captcha is actually an indication that the other end is human.

[ Parent | on HN ]

Re:Initial Release of Mozilla’s Open Source Speech Recogniti... by yjftsjthsd-h on Thursday November 30, 2017 @12:42AM (#15813743)

Pretty sure that's been done with existing voice to text systems. So, yes :)

[ Parent | on HN ]