HINDI SPEECH RECOGNITION TECHNIQUE USING HTK

This paper is based on SR system. In the speech recognition process computer takes a voice signal which is recorded using a microphone and converted into words in real-time. This SR system has been developed using different feature extraction techniques which include MFCC, HMM. All are used as the classifier. ASR i.e. automated speech recognition is program or we can called it as a machine, and it has ability to recognize the voice signal (speech signal or voice commands) or take dictation which involves the ability to match a voice pattern opposite to a given vocabulary.  HTK i.e. The Hidden Markov model Toolkit is used to develop the SR System. HMM consist of the Acoustic word model which is used to recognize the isolated word. In this paper, we collect Hindi database, with a vocabulary size a bit extended. HMM has been implemented using the HTK Toolkit.