Abstract: The invention allows modeling and searching patterns in a data sequence. A data sequence is analyzed to determine at least two data elements that, when replaced with one replacement data element, will cause a metric of irregularity of the data sequence being analyzed to be maximized. The replacement data element is not included in the data sequence being analyzed. The determined at least two data elements are replaced with the replacement data element thereby generating a residual data sequence. The steps of analyzing and replacing are iterated until reaching a predetermined value of an iteration threshold, wherein with each iteration the analyzing and replacing are applied to the residual data sequence generated in the preceding iteration.

Abstract: A method is for a pattern discovery and recognition, wherein a first sequence comprising first sequence symbols relating to a concept and a tag associated to the first sequence are received, transition probability matrices are obtained from transition frequency matrices representing the frequency data of the occurrences of the transitions between the first sequence symbols at different distances in the first sequence, and the transition probability matrices for each tag and each distance are learnt for obtaining an activation function determining the concept occurring in a second sequence. A computer program product and an apparatus are for executing the pattern discovery and recognition method.

Abstract: The invention allows modeling and searching patterns in a data sequence. A data sequence is analyzed to determine at least two data elements that, when replaced with one replacement data element, will cause a metric of irregularity of the data sequence being analyzed to be maximized. The replacement data element is not included in the data sequence being analyzed. The determined at least two data elements are replaced with the replacement data element thereby generating a residual data sequence. The steps of analyzing and replacing are iterated until reaching a predetermined value of an iteration threshold, wherein with each iteration the analyzing and replacing are applied to the residual data sequence generated in the preceding iteration.

Abstract: A method is for a pattern discovery and recognition, wherein a first sequence comprising first sequence symbols relating to a concept and a tag associated to the first sequence are received, transition probability matrices are obtained from transition frequency matrices representing the frequency data of the occurrences of the transitions between the first sequence symbols at different distances in the first sequence, and the transition probability matrices for each tag and each distance are learnt for obtaining an activation function determining the concept occurring in a second sequence. A computer program product and an apparatus are for executing the pattern discovery and recognition method.

Abstract: Speech and music phonation formed by spectral formants is synthesized by a composite filter containing parallel filters in cascade. The composite filter design is generated by partial-function expansion of the approximate sound channel transfer function ##EQU1## and the composite filter is implemented with mutually adjacent formants in cascade filter elements.