Speech Recognition

This paper aims to build a Bangla speech sentence recognition system by Hidden Markov Model (HMM). This system includes two phases; such as, a feature extraction phase to generate speech features from the Bangla speech sentence and a recognition phase to identify the Bangla speech sentence. The Mel Frequency Cepstral Coefficients (MFCCs) have been used to generate the features from the input Bangla speech sentences. These MFCCs features were used in the HMM based speech recognizer to identify the Bangla speech sentences. Train data with the different types of HMM training algorithm. In both training and testing process, one hidden Markov model for each sentence has been implemented. The models were trained with labeled training data, and the classification was performed by passing the features to each model and selected the best match. The development and experiments were done on MATLAB 2010 and the learning behavior of the algorithms was tested on different Bangla speech sentences from different speakers.

Life is a blessing from the graces of God that he granted to all His creatures. God has excelled in creating this life in its most beautiful form, making the difference of people and the difference of graces among them a cornerstone for enjoying life. Created nature around him, which fascinates hearts, and some enjoy hearing the melody of nature and the chirping of birds and the chants of the seas. The situation regarding the deaf and dumb category is different, because life on a daily basis faces the deaf and dumb category with various difficulties, some of which are similar to what other natural individuals face, Some of the others are his own, that is, they are caused by the problems he suffers because of his disability, and the deaf-dumb tries to continue living relying on his attempt to be able to adapt to the conditions of his life, so they succeed and fail at times. The greater challenge for the deafdumb is to strive all possible ways to communicate with the society easily and confidently. They face many problems because most of the individuals they interact may lack knowledge of communicating using sign language. This research aims to reach solutions to overcome this problem by proposing an application to communicate for the Deaf and dumb. This application will help the public to understand the sign language used by deaf and dumb individuals. Therefore, the deaf and dumb group can communicate with people who do not know sign language without feeling embarrassed.