Speech recognition by computer - "A survey article "

Automatic Speech Recognition (ASR) has been gaining wide interest in recent years. Many improvements have been realized since 50 years but computers are still not able to understand every single word pronounced by everyone. Speech Recognition is still a very cumbersome problem. There are quite a lot of difficulties. Contemporary ASR systems are composed of a feature processing stage (front-end processing), which aims at extracting the linguistic message while suppressing non-linguistic source sources of variability, and a classification stage (back - end processing), include language modeling, that identifies the feature vectors with linguistic classes. The aim of this survey is to make an over-view for the current ASR techniques in its two stages, front and back end processing.