Abstract: An apparatus for recording speech for subsequent generation of a text includes an acoustic input (M) and an acoustic output (L) for inputting and outputting analog speech respectively. An analog-to-digital/digital-to-analog (AD/DA) converter converts the inputted analog speech into a digitized speech and converts digitized speech into analog speech. A preprocessor (VV) preprocesses the digitized speech converted by the converter (AD/DA), and extracts spectral component characteristics from the digitized speech. A digital memory (MEM) stores the digitized preprocessed speech and a controller (CON) controls an execution of inputted operating functions by at least one of the preprocessor and the digital memory.

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: Recognition of speech with successive expansion of a reference vocabulary, can be used for automatic telephone dialing by voice input. Neural and conventional recognition methods are performed in parallel so that during training and configuration of the neural network, a conventional recognizer operating according to the dynamic programming principle has available newly added word patterns as references for immediate use in recognition. Upon completion of the training and configuration, the neural network takes over the recognition of the now expanded vocabulary.

Abstract: A method for recognizing spoken words of a speech includes extracting feature vectors from a speech signal which corresponds to a spoken phrase, and segmenting and classifying the successive extracted feature vectors into syllable oriented word subunits by means of a stored supply of word subunits to form a set of hypotheses. The set of hypotheses is used to generate, by three dimensional time dynamic comparision, a set of word hypotheses by comparing the segmented and classified word subunits with standard pronunciations and pronunciation variants of a plurality of words stored in a reference pattern vocabulary. The generated set of word hypotheses are then subjected to syntactic analysis to determine the spoken phrase.