News for hackers. Stuff that matters.
Re:Rest in Peas: The Unrecognized Death of Speech Recognition by TravisAllison on Sunday May 02, 2010 @10:12PM (#1313753)
Surprising fact despite what your smartphone tells you: speech recognition in general situations hasn't improved since 2001. A good exposition of why Norvig and Google's approach of using statistical analysis may be approaching a dead end.
Re:Rest in Peas: The Unrecognized Death of Speech Recognition by Tichy on Monday May 03, 2010 @08:43AM (#1314628)
I think something must be wrong with Norvig's approach, because humans can learn a lot faster. We don't need one billion voice samples to learn understanding. So there must be a better way than the ginormous dataset approach.
Re:Rest in Peas: The Unrecognized Death of Speech Recognition by eru on Monday May 03, 2010 @08:31PM (#1316582)
Why? Perhaps your genes have been trained (=evolved) on big datasets to produces good speech recognizers.