Abstract: Speech is the most usual form of human communication and speech processing has been one of the most stimulating expanses of signal processing. Speech recognition is the process of automatically recognizing the spoken words of person based on information in speech signal. Speech technology and human computer interaction systems have witnessed a steady and significant improvement over the last two decades. Now – a - days, speech technologies are commercially available for an unlimited but exciting range of tasks. Using these technologies machines are able to respond correctly and dependably to human voices, and provide useful and valuable services. Recent research concentrates on developing systems that would be much more robust against unpredictability in environment, speaker and language. Hence today researchers mainly focus on Speech Recognition systems with a large vocabulary that support speaker independent operation with continuous speech in different languages.
Keywords: Speech Recognition; Feature Extraction; MFCC; LPC; ANN; VQ; HMM.