Binary Features of Speech Signal for Recognition Mijanur Rahman Md.1,*, Khatun Fatema2,**, Islam Md. Saiful3,***, Bhuiyan Md. Al-Amin4,**** 1Associate Professor, Department of Computer Science and Engineering, Jatiya Kabi Kazi Nazrul Islam University, Bangladesh 2Lecturer, Department of Electrical and Electronic Engineering, Hamdard University, Bangladesh 3Assistant Professor, Department of Computer Science and Engineering, Jatiya Kabi Kazi Nazrul Islam University, Bangladesh 4Professor, Department Computer Engineering, King Faisal University, Saudi Arabia *(*Corresponding author) Email id: *mijanjkkniu@gmail.com
**fatema_aece@yahoo.com
***sailfulmath@yahoo.com
****alamin_bhuiyan@yahoo.com
Abstract Speech feature extraction is the mathematical representation of the speech file, which converts the speech waveform to some type of parametric representation for further analysis and processing in speech recognition. A good feature may produce a good result for any recognition system. This paper presents a simple and novel feature extraction approach for extracting binary features of Bangla speech words. This technique is based on frequency-domain signal features and dynamic thresholding method. First the frequency-domain signal feature, i.e., spectrogram feature is computed from the original speech words and then the binary features of these speech words are computed by using the dynamic thresholding technique. The developed system has been justified with several Bangla speech words. To test and analyse theses binary features, a speech recognition module has been developed. The speech recognition is done by using the neural network with back-propagation training algorithm. All the algorithms used in this research are implemented in MATLAB and the implemented speech recognition system achieved recognition accuracy of 96%. Top Keywords Backpropagation, Dynamic thresholding, Feature extraction, Neural networks, Spectrogram, Speech recognition, Transfer function. Top |