Title :
Speech recognition with the discrete rectangular wave transform
Author :
Kim, D.Y. ; Stanton, B.J. ; Ersoy, O.K. ; Jamieson, L.H.
Author_Institution :
Sch. of Electr. Eng., Purdue Univ., West Lafayette, IN, USA
Abstract :
Speaker and phoneme recognition is investigated based on the discrete rectangular wave transform (DRWT). The DRWT is one of the discrete Fourier preprocessing transforms (DFPTs) 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
Keywords :
fast Fourier transforms; speech recognition; DFT; discrete Fourier preprocessing transforms; discrete Fourier transform; discrete rectangular wave transform; discrete trigonometric transforms; phoneme recognition; recognition experiments; speaker recognition; speech recognition; speech spectrograms; two-stage algorithms; Data structures; Discrete Fourier transforms; Discrete transforms; Euclidean distance; Fourier transforms; Signal generators; Spectrogram; Speech recognition; Testing; Wave functions;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1988. ICASSP-88., 1988 International Conference on
Conference_Location :
New York, NY
DOI :
10.1109/ICASSP.1988.196661
