Uses neural network the speaker independent isolation isolated spoken word recognition system

摘要

The method for speaker independent isolated word recognition is based on a hybrid recognition system, which uses neural networks, availing itself of its parallel processing to improve recognition and optimize system for what concerns time and memory while it keeps some of the consolidated aspects of recognition techniques. Complete words are modeled with left-to-right Markov model automata with recursion on states, each of which corresponds to an acoustic portion of the word, and recognition is obtained by performing a dynamic programming according to the Viterbi algorithm on all automata in order to detect the one having the minimum cost path to which corresponds the recognized word, the emission probabilities being computed through a neural network with feedback, trained in an original way, and the transition probabilities being suitably estimated. IMAGE