Speech recognition technology sees its most recent breakthrough at Microsoft Research. This new model builds upon the latest research in speech recognition involving a model called Deep Neural Networks (DNN), replacing the previously predominant Hidden Markov Model(HMM).
"Toward this end, we present a computational model for speech recognition that is inspired by several interrelated strands of research in phonology, acoustic phonetics, speech perception, and neuroscience." " a hierarchical framework where each layer is designed to capture a set of distinctive feature landmarks. For each feature, a specialized acoustic representation is constructed in which that feature is easy to detect". the video demo http://research.microsoft.com/apps/video/default.aspx?id=175450 article 1(lots of math, more computational) Acoustic Modeling using Deep Belief Networks http://www.cs.toronto.edu/~gdahl/papers/speechDBN_jrnl.pdf article 2(more accessible for phonetician and generic) http://old-site.clsp.jhu.edu/~ajansen/papers/ICASSP2008.pdf news story http://research.microsoft.com/en-us/news/features/speechrecognition-082911.aspx
0 Comments
Leave a Reply. |
NEWSLOG
|