Abstract: A method and system are provided for alleviating the harmful effects of convolutional distortions of speech, such as the effect of a telecommunication channel, on the performance of an automatic speech recognizer (ASR). The technique is based on the filtering of time trajectories of an auditory-like spectrum derived from the Perceptual Linear Predictive (PLP) method of speech parameter estimation.

Abstract: An imaging system generates images of the interior of an object using radiation which is attenuated and scattered by the interior of the object. The object is radiated at a number of points near the exterior of the object, and the radiation emerging from the object is measured at an array of exit points near the exterior of the object. The interior of the object is modelled as an array of volume elements called voxels. Each voxel is modelled as having scattering and attenuation properties, represented by numerical coefficients. The system computes the intensity of radiation that would emerge from the object at the exit points if the interior of the object were characterized by a currently assigned set of values for the scattering and attenuation coefficients. Then, the differences between the measured intensities and the computer intensities are used to compute an error function relates to the magnitude of the errors in the reconstruction.