Advances in Non-Linear Modeling for Speech Processing

Non-linear aeroacoustic modeling approach is used to estimate the important fine-structure speech events, which are not revealed by the short time Fourier transform (STFT). This book includes advanced topics in non-linear estimation and modeling techniques along with their applications to speaker recognition.

Different features derived using above non-linear modeling techniques are used to develop a speaker identification system. Finally, it is shown that, the fusion of speech production and speech perception mechanisms can lead to a robust feature set.

From the Contents: Speech production mechanism.- Linear speech production model.- Nonlinearity in speech production.- Nonlinear dynamic system model.- Speech perception mechanism.- Summary.- Autoregressive models.- Linear autoregressive model.- Nonlinear autoregressive model.- Nonlinear measurement and modeling using Teager energy operator.- Teager energy operator (TEO).- Vocal tract aeroacoustic flow.- Energy measurement.- Energy separation.- Noise suppression using TEO.