Abstract: A test pattern generator includes a random pattern generator and a shift register. The random pattern generator generates a series of digits which are input to the shift register and stored therein. Each digit output by the random pattern generator has a probability of having a first value, such as representing "1". The output probability of the random pattern generator is adjustable. The shift register has a plurality of outputs for outputting a test pattern comprising the stored digits. The shift register includes a series of latches and at least a first logic circuit connecting the output of the random pattern generator to the input of a first latch, or connecting the output of a latch to the input of a next adjacent latch. In a first state, the logic circuit has an output probability which is independent of the output probability of the random pattern generator. In a second state, the logic circuit has an output probability which is dependent on the output probability of the random pattern generator.

Abstract: A method and apparatus for modeling words based on match scores representing (a) the closeness of a match between probabilistic word models and the acoustic features of at least two utterances, and (b) the closeness of a match between word models and the spelling of the word. A match score is calculated for a selection set of one or more probabilistic word models. A match score is also calculated for an expansion set comprising the probabilistic word models in the selection set and one probabilistic word model from a candidate set. If the expansion set match score improves the selection set match score by a selected nonzero threshold value, the word is modelled with the word models in the expansion set. If the expansion set match score does not improve the selection set match score by the selected nonzero threshold value, the word is modelled with the words in the selection set.

Abstract: A speech recognition system displays a source text of one or more words in a source language. The system has an acoustic processor for generating a sequence of coded representations of an utterance to be recognized. The utterance comprises a series of one or more words in a target language different from the source language. A set of one or more speech hypotheses, each comprising one or more words from the target language, are produced. Each speech hypothesis is modeled with an acoustic model. An acoustic match score for each speech hypothesis comprises an estimate of the closeness of a match between the acoustic model of the speech hypothesis and the sequence of coded representations of the utterance. A translation match score for each speech hypothesis comprises an estimate of the probability of occurrence of the speech hypothesis given the occurrence of the source text. A hypothesis score for each hypothesis comprises a combination of the acoustic match score and the translation match score.

Abstract: An elastic-matching alignment technique for providing an averaged prototype in a handwriting recognition system that improves the alignment of parametric representations of recognized characters to be averaged. The point-to-point correspondence resulting from an elastic match of two characters is obtained by using backpointers during the calculation of the match. A character is added to a prototype set if it is new or is not correctly recognized within a fixed threshold. Otherwise, the character is averaged into the closest prototype of its class to provide a new average prototype.

Abstract: In speech recognition and speech coding, the values of at least two features of an utterance are measured during a series of time intervals to produce a series of feature vector signals. A plurality of single-dimension prototype vector signals having only one parameter value are stored. At least two single-dimension prototype vector signals having parameter values representing first feature values, and at least two other single-dimension prototype vector signals have parameter values representing second feature values. A plurality of compound-dimension prototype vector signals have unique identification values and comprise one first-dimension and one second-dimension prototype vector signal. At least two compound-dimension prototype vector signals comprise the same first-dimension prototype vector signal. The feature values of each feature vector signal are compared to the parameter values of the compound-dimension prototype vector signals to obtain prototype match scores.

Abstract: A speech coding apparatus and method for use in a speech recognition apparatus and method. The value of at least one feature of an utterance is measured during each of a series of successive time intervals to produce a series of feature vector signals representing the feature values. A plurality of prototype vector signals, each having at least one parameter value and a unique identification value are stored. The closeness of the feature vector signal is compared to the parameter values of the prototype vector signals to obtain prototype match scores for the feature value signal and each prototype vector signal. The identification value of the prototype vector signal having the best prototype match score is output as a coded representation signal of the feature vector signal. Speaker-dependent prototype vector signals are generated from both synthesized training vector signals and measured training vector signals.

Abstract: A solid modeling system for combining a plurality of geometric model elements to form a whole model. The whole model is represented as a collection of non-manifold boundary elements. A data file maintains a record of the correspondence between each non-manifold boundary element and each geometric model element of the whole model, to permit easy and fast modification of the whole model.

Abstract: An apparatus for generating a set of acoustic prototype signals for encoding speech includes a memory for storing a training script model comprising a series of word-segment models. Each word-segment model comprises a series of elementary models. An acoustic measure is provided for measuring the value of at least one feature of an utterance of the training script during each of a series of time intervals to produce a series of feature vector signals representing the feature values of the utterance. An acoustic matcher is provided for estimating at least one path through the training script model which would produce the entire series of measured feature vector signals. From the estimated path, the elementary model in the training script model which would produce each feature vector signal is estimated. The apparatus further comprises a cluster processor for clustering the feature vector signals into a plurality of clusters.

Abstract: A language generator for a speech recognition apparatus scores a word-series hypothesis by combining individual scores for each word in the hypothesis. The hypothesis score for a single word comprises a combination of the estimated conditional probability of occurrence of a first class of words comprising the word being scored, given the occurrence of a context comprising the words in the word-series hypothesis other than the word being scored, and the estimated conditional probability of occurrence of the word being scored given the occurrence of the first class of words, and given the occurrence of the context. An apparatus and method are provided for classifying multiple series of words for the purpose of obtaining useful hypothesis scores in the language generator and speech recognition apparatus.

Abstract: A method and apparatus for finding the best or near best binary classification of a set of observed events, according to a predictor feature X so as to minimize the uncertainty in the value of a category feature Y. Each feature has three or more possible values. First, the predictor feature value and the category feature value of each event is measured. The events are then split, arbitrarily, into two sets of predictor feature values. From the two sets of predictor feature values, an optimum pair of sets of category feature values is found having the lowest uncertainty in the value of the predictor feature. From the two optimum sets of category feature values, an optimum pair of sets is found having the lowest uncertainty in the value of the category feature. An event is then classified according to whether its predictor feature value is a member of a set of optimal predictor feature values.

Abstract: A method of detecting and correcting an error in a string of information signals. When each information signal represents a word, the method detects and corrects spelling errors. The method detects and corrects an error which is a properly spelled word, but which is the wrong (not intended) word. For example, the method is capable of detecting and correcting a misspelling of "HORSE" as "HOUSE". In the spelling error detection and correction method, a first word in an input string of words is changed to form a second word different from a first word to form a candidate string of words. The spellings of the first word and the second word are in the spelling dictionary. The probability of occurrence of the input string of words is compared to the product of the probability of occurrence of the candidate string of words multiplied by the probability of misrepresenting the candidate string of words as the input string of words. If the former is greater than or equal to the latter, no correction is made.

Abstract: A speech recognition apparatus and method estimates the next word context for each current candidate word in a speech hypothesis. An initial model of each speech hypothesis comprises a model of a partial hypothesis of zero or more words followed by a model of a candidate word. An initial hypothesis score for each speech hypothesis comprises an estimate of the closeness of a match between the initial model of the speech hypothesis and a sequence of coded representations of the utterance. The speech hypotheses having the best initial hypothesis scores form an initial subset. For each speech hypothesis in the initial subset, the word which is most likely to follow the speech hypothesis is estimated. A revised model of each speech hypothesis in the initial subset comprises a model of the partial hypothesis followed by a revised model of the candidate word. The revised candidate word model is dependent at least on the word which is estimated to be most likely to follow the speech hypothesis.

Abstract: A method and a system for synthesizing speech from unrestricted text, based on the principle of associating a written string of text with a sequence of speech features vectors that most probably model the corresponding speech utterance. The synthesizer is based on the interaction between two different Ergodic Hidden Markov Models: an acoustic model reflecting the constraints on the acoustic arrangement of speech, and a phonetic model interfacing phonemic transcription to the speech features representation.

Abstract: A speech coding and speech recognition apparatus. The value of at least one feature of an utterance is measured over each of a series of successive time intervals to produce a series of feature vector signals. The closeness of the feature value of each feature vector signal to the parameter value of each of a set of prototype vector signals is determined to obtain prototype match scores for each vector signal and each prototype vector signal. For each feature vector signal, first-rank and second-rank scores are associated with the prototype vector signals having the best and second best prototype match scores, respectively. For each feature vector signal, at least the identification value and the rank score of the first-ranked and second-ranked prototype vector signals are output as a coded utterance representation signal of the feature vector signal, to produce a series of coded utterance representation signals.

Abstract: Symbol feature values and contextual feature values of each event in a training set of events are measured. At least two pairs of complementary subsets of observed events are selected. In each pair of complementary subsets of observed events, one subset has contextual features with values in a set C.sub.n, and the other set has contextual features with values in a set C.sub.n, were the sets in C.sub.n and C.sub.n are complementary sets of contextual feature values. For each subset of observed events, the similarity values of the symbol features of the observed events in the subsets are calculated. For each pair of complementary sets of observed events, a "goodness of fit" is the sum of the symbol feature value similarity of the subsets. The sets of contextual feature values associated with the subsets of observed events having the best "goodness of fit" are identified and form context-dependent bases for grouping the observed events into two output sets.

Abstract: In a speech recognition system, apparatus and method for modelling words with label-based Markov models is disclosed. The modelling includes: entering a first speech input, corresponding to words in a vocabulary, into an acoustic processor which converts each spoken word into a sequence of standard labels, where each standard label corresponds to a sound type assignable to an interval of time; representing each standard label as a probabilistic model which has a plurality of states, at least one transition from a state to a state, and at least one settable output probability at some transitions; entering selected acoustic inputs into an acoustic processor which converts the selected acoustic inputs into personalized labels, each personalized label corresponding to a sound type assigned to an interval of time; and setting each output probability as the probability of the standard label represented by a given model producing a particular personalized label at a given transition in the given model.

Abstract: Modeling a word is done by concatenating a series of elemental models to form a word model. At least one elemental model in the series is a composite elemental model formed by combining the starting states of at least first and second primitive elemental models. Each primitive elemental model represents a speech component. The primitive elemental models are combined by a weighted combination of their parameters in proportion to the values of the weighting factors. To tailor the word model to closely represent variations in the pronunciation of the word, the word is uttered a plurality of times by a plurality of different speakers. Constructing word models from composite elemental models, and constructing composite elemental models from primitive elemental models enables word models to represent many variations in the pronunciation of a word.

Abstract: A pattern recognition method and apparatus using dynamic programming in which an input sequence of labels is matched to a set of candidate templates (candidate reference label sequences). The set of candidate reference label sequences is grouped into subsets, where each reference label sequence in a subset has a common root reference label subsequence. Using this set organization, a depth-first search is performed to identify a local optimum template and its local optimum match score with the input sequence of labels. Using the local optimum match score as a threshold, the input sequence of labels is matched to root reference label subsequences, eliminating those root reference label subsequences having match scores above the threshold. Surviving root reference label subsequences having match scores below the threshold remain recognition candidates, and are further investigated.

Abstract: A speech recognition system estimates a set of Poisson intensities for a spoken word, each intensity representing a respectively different word from a vocabulary of words. Each of the functions used to calculate these intensities has two variable parameter values. In a training mode, the system changes the values of the respective variable parameters to optimize the likelihood that the results predicted by the estimates correspond to the actual spoken words. These optimized parameter values are then used by the system, in an operational mode, to recognize spoken words.

Abstract: For circumstance adaption, for example, speaker adaption, confusion coefficients between the labels of the label alphabet for initial training and those for adaption are determined by alignment of adaption speech with the corresponding initially trained Markov model. That is, each piece of adaptation speech is aligned with a corresponding initially trained Markov model by the Viterbi algorithm, and each label in the adaption speech is mapped onto one of the states of the Markov models. In respect of each adaptation lable ID, the parameter values for each initial training label of the states which are mapped onto the adaptation label in concern are accumulated and normalized to generate a confusion coefficient between each initial training label and each adaptation label. The parameter table of each Markov model is rewritten in respect of the adaptation label alphabet using the confusion coefficients.