Third International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications (MAVEBA 2003)
The nonlinear speech signal decomposition based on Volterra-Wiener functional series is described. The solution of speech recognition problem by means of measuring Wiener kernels is proposed. The recognition system of speech signal is considered for speech phoneme identification.
Index Terms. Nonlinear signal decomposition, Wiener kernels, phoneme recognition
Full Paper (reprinted with permission from Firenze University Press)
Bibliographic reference. Krot, A. M. / Tkachova, P. P. (2003): "Algorithm of phoneme identification using fast measurement of Wiener kernels of speech signals", In MAVEBA-2003, 107-110.