Automatic Segmentation of Punjabi Speech into Syllable-Like Units using Group Delay A Review

The basic building blocks of a speech segmentation system are its units. Thus it’s an important stage to select appropriate units into which the continuous speech needs to be segmented. The syllable like units is found to be the better representative for Indian languages. Punjabi is the most widely used language, thus this paper describes the automatic segmentation of Punjabi speech into syllable like units using group delay method. The STE (Short Term Energy) and ZCR (Zero Crossing Rate) are used to evaluate the basic characteristic of speech. In case of continuous speech group delay approach is used i.e. the negative derivative of Fourier transformations.