Saraswati college of Engg.

Speech recognition is an important component of biological identification which is an integrated technology of acoustics, signal processing and artificial intelligence. Recognition systems based on hidden Markov models are effective under particular circumstances, but do suffer from some major limitations that limit applicability of ASR technology in real-world environments. Attempts were made to overcome these limitations with the adoption of artificial neural networks as an alternative paradigm for ASR, but ANNs were unsuccessful in dealing with long time sequences of speech signals. So taking the limitations and advantages of both the systems it was proposed to combine HMM and ANN within a single, hybrid architecture. The goal in hybrid systems for ASR is to take advantage from the properties of both HMM and ANNs, improving flexibility and ASR performance For Speech recognition features from speech sample are extracted & mapping is done using Artificial Neural Networks. Multilayer pattern mapping neural network, which works on the principle of back propagation algorithm is proposed. Finally Speaker Recognition is done using Hidden Markov Model (HMM). The specialty of this model is the flexible and expandable hidden layer for recognition Keywords-Speech Recognition, Artificial Neural network, Speaker Recognition, Hidden Markov Mode