Abstract: Sound-generating processes are classified using at least one sensor for detecting sound signals caused by the sound-generating processes. A storage stores a reference model which has statistical distribution parameters for predetermined characteristics of a sound signal. An adaptation unit extracts the characteristic from the detected sound signals of the processes and calculates a similarity between the sound signals detected based on the extracted characteristics for grouping the processes into various process clusters having sound signals that are similar to each other. The adaptation unit adapts the stored reference model as a function of the statistical distribution parameters of those processes in a process cluster having the maximum number of processes, then a classification unit classifies the sound-generating processes based on the adapted model.

Abstract: Sound-generating processes are classified using at least one sensor for detecting sound signals caused by the sound-generating processes. A storage stores a reference model which has statistical distribution parameters for predetermined characteristics of a sound signal. An adaptation unit extracts the characteristic from the detected sound signals of the processes and calculates a similarity between the sound signals detected based on the extracted characteristics for grouping the processes into various process clusters having sound signals that are similar to each other. The adaptation unit adapts the stored reference model as a function of the statistical distribution parameters of those processes in a process cluster having the maximum number of processes, then a classification unit classifies the sound-generating processes based on the adapted model.

Abstract: Answering machines and voice mailbox systems are normally provided in modern communications systems. When a communications subscriber is temporarily unreachable at the location of their fixed network telephone, incoming calls can be accepted by an answering machine and voice messages can be recorded. The drawback of this procedure is that messages containing important information cannot be promptly conveyed to the communications subscriber. During incoming voice messages, their content is evaluated with the aid of a speech recognition system. As a result, content-based prioritization of voice messages is made possible in a communications system and the receiver is notified of the incoming voice messages according to the prioritization.

Abstract: In speech recognition, phonemes of a language are modelled by a hidden Markov model, whereby each status of the hidden Markov model is described by a probability density function. For speech recognition of a modified vocabulary, the probability density function is split into a first and into a second probability density function. As a result thereof, it is possible to compensate variations in the speaking habits of a speaker or to add a new word to the vocabulary of the speech recognition unit and thereby assure that this new word is distinguished with adequate quality from the words already present in the speech recognition unit and is thus recognized.

Abstract: A method is described for compressing the storage space required by HMM prototypes in an electronic memory. For this purpose prescribed HMM prototypes are mapped onto compressed HMM prototypes with the aid of a neural network (encoder). These can be stored with a smaller storage space than the uncompressed HMM prototypes. A second neural network (decoder) serves to reconstruct the HMM prototypes.

Abstract: In the recognition of spoken language, phonemes of the language are modelled by hidden Markov models. A modified hidden Markov model includes a conditional probability of a feature vector dependent on chronologically preceding feature vectors and, optionally, additionally comprises a conditional probability of a respectively current status. A global search for recognizing a word sequence in the spoken language is implemented with the modified hidden Markov model.

Abstract: A keyword is recognized in spoken language by assuming a start of this keyword is at every sampling time. An attempt is then made to image this keyword onto a sequence of HMM statusses that represent the keyword. The best path in a presentation space is determined with the Viterbi algorithm; and a local confidence standard is employed instead of the emission probability used in the Viterbi algorithm. When a global confidence standard that is composed of local confidence standards downwardly crosses a lower barrier for the best Viterbi path, then the keyword is recognized; and the sampling time assumed as start of the keyword is confirmed.

Abstract: When adapting a lexicon in a speech recognition system, a code book of hidden Markov sound models made available with a speech recognition system is adapted for specific applications. These applications are thereby defined by a lexicon of the application that is modified by the user. The adaption ensues during the operation and occurs by a shift of the stored mid-point vector of the probability density distributions of hidden Markov models in the direction of a recognized feature vector of sound expressions and with reference to the specifically employed hidden Markov models. Compared to standard methods, this method has the advantage that it ensues on-line and that it assures a very high recognition rate given a low calculating outlay. Further, the outlay for training specific sound models for corresponding applications is avoided.

Abstract: A method is described for compressing the storage space required by HMM prototypes in an electronic memory. For this purpose prescribed HMM prototypes are mapped onto compressed HMM prototypes with the aid of a neural network (encoder). These can be stored with a smaller storage space than the uncompressed HMM prototypes. A second neural network (decoder) serves to reconstruct the HMM prototypes.

Abstract: In an echo suppressor and a method for the operation thereof in a speech input system, particularly suited for use in speech input systems having extremely long echo paths (approximately 50 ms), an input request of the speech recognition system as well as the incoming speech signal (which has been corrupted by the input request) are fast-Fourier transformed, and the transformed signals are divided into a number of sub-bands in order to estimate corresponding sub-band echo signals. This occurs with individual adaptive filter stages that utilize the NLMS algorithm. Due to the division into sub-bands and a reduction of the number of these sub-bands, the calculating outlay is minimized and the sampling rate can be reduced. The calculating procedure in the estimating of the echo signal part is thus reduced.

Abstract: The invention expands a feature extraction unit of a type known in the art with an adaptive channel compensation. The filter coefficients for a high-pass filter for eliminating the chronologically sliding average are set time-dependently with the adaptive channel compensation. As a result, a faster channel adaptation, and a better error compensation in the speech feature extraction are achieved, leading to a more reliable speech recognition. The parameters for the individual function blocks of the feature extraction unit are determined and stored in advance for specific speech transmission channels such as in mobile radio telephone, ISDN and analog speech transmission. The speech recognition with the assistance of the feature extraction unit can subsequently then ensue in channel-associated fashion with the stored parameters values.