Analytical Review of Feature Extraction Technique for Automatic Speech Recognition

Speech recognition is a multileveled pattern recognition task, in which acoustical signalsare examined and structured into a hierarchy of subword units (e. g. , phonemes), words, phrases, and sentences. Each level may provide additional temporal constraints, e. g. , knownword pronunciations or legal word sequences, which can compensate for errors or uncertainties at lower levels. This hierarchy of constraints can best be exploited by combiningdecisions probabilistically at all lower levels, and making discrete decisions only at thehighest level. .