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
article 1(lots of math, more computational)
Acoustic Modeling using Deep Belief Networks
article 2(more accessible for phonetician and generic)