Abstrait

Speech Processing Of Tamil Language With Back Propagation Neural Network And Semi- Supervised Traning

N.Pushpa, R.Revathi, C.Ramya, S.Shahul Hameed

Speech recognition has been an active research topic for more than 50 years. Interacting with the computer through speech is one of the active scientific research fields particularly for the disable community who face variety of difficulties to use the computer. Such research in Automatic Speech Recognition (ASR) is investigated for different languages because each language has its specific features. Especially the need for ASR system in Tamil language has been increased widely in the last few years. In this paper, a speech recognition system for individually spoken word in Tamil language using multilayer feed forward network is presented. To implement the above system, initially the input signal is preprocessed using four types of filters namely preemphasis, median, average and Butterworth bandstop filter in order to remove the background noise and to enhance the signal. The performance of these filters are measured based on MSE and PSNR values. The best filtered signal is taken as the input for the further process of ASR system. The speech features being the major part of speech recognition system, are analyzed and extracted via Linear Predictive Cepstral Coefficients (LPCC). These feature vectors are given as the input to the Feed-Forward Neural Network for classifying and recognizing Tamil spoken word. We propose a technique for training deep neural networks (DNNs) as data-driven feature front-ends for large vocabulary continuous speech recognition (LVCSR) in low resource settings. To circumvent the lack of sufficient training data for acoustic modelling in these scenarios, we use transcribed multilingual data and semi-supervised training to build the proposed feature front-ends.