SPEECH RECOGNITION WITH THE DISCRET RECTANGULAR WAVE TRANSFORM
D. Y. Kim, B.J. Stanton, K. Ersoy · 1988
Speaker and phoneme recognition is investi ated based on the discrete rectangular wave transform (DRWTT. The DRWT is one of the discrete Fourier preprocessing transforms (DFPT’s) which corresponds to the first stage in two-stage algorithms to represent discrete trigonometric transforms such as the discrete Fourier transform (DFT). The DRWT is much faster and easier to implement than the DFT. The recognition experiments performed also show that performance of recognition based on DRWT speech spectrograms is comparable to the performance of recognition based on DFT speech spectrograms. In this article, speaker identification and phoneme