Abstract: An integrated circuit contains a processor (DSP) for the processing of data, at least two modules (M1, M2, M3) for the processing of data packets selected by the processor according to differing operation regulations, and a router (ROUTER) which is connected to all modules (M1, M2, M3) and to the processor (DSP) for the purpose of controlling the data traffic between the processor (DSP) and the modules (M1, M2, M3). The router is suited to receive from the processor (DSP) data packets and associated instructions, to execute special operations for individual data packets which can be executed by the modules (M1, M2, M3) in specified sequence, to coordinate autonomously the control of the sequences, to transfer the data packets to the appropriate modules (M1, M2, M3), and to transfer the data packets after they have been processed according to the specified instructions to the processor (DSP).

Abstract: Through crosstalk on lines, interference from current transmission lines or line echoes, the useable signal is superimposed by different interference signals. The task is to find a procedure for reducing interference which, compared to the current state of the art, can be achieved with a smaller amount of computing input and is suited to both the reduction of quasi steady-state and non-steady interference. In this, the interference of a received signal is classified with regards to characteristics in the time range as a click, crackle, rumble or noise interference signal. The time range in which the interference occurs is marked. Depending on the interference type, interference blanking and/or an interpolation of the useable signal and/or a subtraction of the interference signal from the useable signal and/or a regeneration of the useable signal is carried out.

Abstract: Neural networks are used to classify objects automatically by means of Doppler-broadened radar echo signals. The classification device KK contains a neural network (NET, NET2) which has an input layer (IL) of input nodes (IN1, . . . , IN57) for features (M) of the Doppler-broadened radar echo signals, and an output layer (OL) of output nodes (ON1, ON2, ON3) for predetermined classes to which the objects can be allocated. The neural network (NET, NET2) is adapted to the external conditions prevailing at the time of the classification operation. The adaptation takes place either via accessible input nodes (ZN1, ZN2) into which control information (SI) can be entered, and which cause the neural network (NET) to adapt to one or to several external influence factors, or via a selection device (SEL) which, from the parameters (P1, . . .

Abstract: Speech recognition of Lombard-induced speech at a high rate of recognition is shown using a neural network (NN) utilizing nonlinear imaging characteristics. In a training phase, systematic parameter changes of Lombard-induced speech are trained to a neural network. In a speech recognition phase, imaging of Lombard-induced speech patterns to Lombard-free speech patterns takes place through the trained parameter changes.

Abstract: A neural network for noise reduction for speech recognition in a noisy environment uses an algorithm for automatic network generation which automatically selects a suitable signal representation. Nodes may be added to the input layer of the neural network successively, with a new node being trained by calculating and minimizing a mapping error. A squared mapping error may be formed and the mapping error may be assigned a weight dependent on the importance of the vectors. In addition, a neural network that performs neural noise reduction by reducing, in a training phase, a mapping error between noise-free vectors at an output of the neural network and noise-reduced vectors at the output of the neural network using an iterative process, has the mapping error further reduced by additional information which is selected from a suitable signal representation at the input of the neural network.