IBM Speech Recognition, 1986 - 0 views
-
johannessimon81 on 09 Nov 13Interesting historical perspective. Progress since the late '80 really seems to be fairly slow. ?: Do we need to wait for the singularity until speech recognition works without flaws?
- ...1 more comment...
-
johannessimon81 on 13 Nov 13"I thought I would give it a try on my android sexy seems to work pretty well and I'm speaking more less at normal speed" Actually I was speaking as fast as I could because it was for the google search input - if you make a pause it will think you finished your input and start the query. Also you might notice that Android thinks it is "android sexy" - this was meant to be "on my Android. THIS seems to work...". Still it is not too bad - maybe in a year or two they have it working. Of course it might also be that I just use the word "sexy" randomly... :-\
-
Paul N on 13 Nov 13The problem is that we don't yet understand how speech in humans actually works. As long as we merely build either inference or statistical language models we'll never get perfect speech recognition. A lot of recognition in humans has a predictive/expectational basis to it that stems from our understanding of higher lvl concepts and context awareness. Sadly I suspect that as long as machines remain unembodied in their perceptual abilities their ability to either properly recognize sounds/speech or objects and other features will never reach perfection.