Assistant Professor/Department of ECE

commonly used for speech decoding. Initially, n numbers of speech signals of n number of speakers are stored in the database. Then the features of the real time input signal is extracted and is compared with that of the signals stored in database using the MFCC (Mel-Frequency Cepstral Coefficients) algorithm. The speech recognition is first tested in the absence of noisy environments and then it is tested in the presence of noisy environments. The algorithm used to test the speech signal authentication in the absence of noisy environments is performed using MFCC and HMM algorithms. The proposed algorithm is applicable for adaptively estimating and removing background noise from speech signals. Unlike noise reduction and speech enhancement algorithms currently available on the market, the new algorithm is capable of cleaning noisy speech even in severe noisy environments without any distortion to the speech signal. The proposed algorithm called Modified Hidden Markov Model (Modified HMM) and Modified Mel-Frequency Cepstral Coefficients (Modified MFCC) are capable of doing Speech signal enhancement and recognition and the Expectation Maximization (EM) algorithm is used to estimate the features of the enhanced speech signal. This project may be used in various application areas such as, for authentication number of employees working in offices, in military applications and also in all possible security applications