Isolated Word Speech Recognition Using Mixed Transform

Abstract

Methods of speech recognition have been the subject of several studies over the past decade. Speech recognition has been one of the most exciting areas of the signal processing. Mixed transform is a useful tool for speech signal processing; it is developed for its abilities of improvement in feature extraction. Speech recognition includes three important stages, preprocessing, feature extraction, and classification. Recognition accuracy is so affected by the features extraction stage; therefore different models of mixed transform for feature extraction were proposed. The properties of the recorded isolated word will be 1-D, which achieve the conversion of each 1-D word into a 2-D form. The second step of the word recognizer requires, the application of 2-D FFT, Radon transform, the 1-D IFFT,and 1-D discrete wavelet transforms were used in the first proposed model, while discrete multicircularlet transform was used in the second proposed model. The final stage of the proposed models includes the use of the dynamic time warping algorithm for recognition tasks. The performance of the proposed systems was evaluated using forty different isolated Arabic words that are recorded fifteen times in a studio for speaker dependant. The result shows recognition accuracy of (91% and 89%) using discrete wavelet transform type Daubechies (Db1) and (Db4) respectively, and the accuracy score between (87%-93%) was achieved usingdiscrete multicircularlet transform for 9 sub bands.