News for hackers. Stuff that matters.

A comment on Researchers achieve speech recognition milestone. Parent comment

Re:Researchers achieve speech recognition milestone by cptskippy on Wednesday September 14, 2016 @07:19PM (#12502047)
Exactly, when SR has a low confidence level it needs to ask for you to repeat yourself. Not just choose the highest confidence match and hope for the best.
[ Parent | on HN ]
Re:Researchers achieve speech recognition milestone by randyrand on Wednesday September 14, 2016 @09:37PM (#12502714)
Siri underlines words its not sure about. Then if you click it, it gives you a menu of potential other candidates.

Seems like a good approach.

[ Parent | on HN ]
Re:Researchers achieve speech recognition milestone by tarikjn on Thursday September 15, 2016 @01:20AM (#12503635)
That's a good start but a probably the wrong interface for it, "non-native" in the context, a command initialized by voice should present the options by voice.
[ Parent | on HN ]
Re:Researchers achieve speech recognition milestone by zaroth on Wednesday September 14, 2016 @10:05PM (#12502825)
It's a valid HCI solution to a technical failure mode. Once the software has advanced to the point where the AI is truly conversational, it is a watershed moment.
[ Parent | on HN ]
Re:Researchers achieve speech recognition milestone by cptskippy on Thursday September 15, 2016 @10:56AM (#12506664)
That's fine for dictation but of little use when driving or other eyes free scenarios.
[ Parent | on HN ]