To accomplish the 5.9 percent error rate, which beats a 6.3 percent record set just last month, the Microsoft team leveraged neural language models resembling associative word clouds. That is, a word like "fast" resides much closer to "fast" than it does to "slow". This allowed the speech recognition engine to generalize between words and better recognize them in context.
Group items matching
in title, tags, annotations or url
3More
Word Lens Offers Real Time Language Translation - Mac Rumors - 0 views
1More
Learn Just the Foreign Language Phrases You Need With TripLingo - 0 views
1More