Abstract: The present invention relates to apparatus and method for segmenting multiple utterances of a vocabulary word in a consistent and coherent manner and determining a Markov model sequence for each segment. A fenemic Markov model corresponds to each label.

Abstract: Apparatus and method for training the statistics of a Markov Model speech recognizer to a subsequent speaker who utters part of a training text after the recognizer has been trained for the statistics of a reference speaker who utters a full training text. Where labels generated by an acoustic processor in response to uttered speech serve as outputs for Markov models, the present apparatus and method determine label output probabilities at transitions in the Markov models corresponding to the subsequent speaker where there is sparse training data. Specifically, label output probabilities for the subsequent speaker are re-parameterized based on confusion matrix entries having values indicative of the similarity between an lth label output of the subsequent speaker and a kth label output for the reference speaker.

Abstract: Speech recognition is improved by splitting each feneme string at a consistent point into a left portion and a right portion. The present invention addresses the problem of constructing fenemic baseforms which take into account variations in pronunciation of words from one utterance thereof to another. Specifically, the invention relates to a method of constructing a fenemic baseform for a word in a vocabulary of word segments including the steps of: (a) transforming multiple utterances of the word into respective strings of fenemes; (b) defining a set of fenemic Markov model phone machines; (c) determining the best single phone machine P.sub.1 for producing the multiple feneme strings; (d) determining the best two phone baseform of the form P.sub.1 P.sub.2 or P.sub.2 P.sub.

Abstract: Continuous speech recognition is improved by use of a known vocabulary and context probabilities. First, the unknown utterance is analyzed as a sequence of phonemes, then each phoneme labelled to form a string of labels. The shortest label interval which is recognized as a word is assigned a storage stack where similar-sounding candidate words are stored. Multiple stack decoding, and liklihood envelope criteria for word path extension decisions, are further features of the system.

Abstract: In a speech recognition system, discrimination between similar-sounding uttered words is improved by weighting the probability vector data stored for the Markov model representing the reference word sequence of phones. The weighting vector is derived for each reference word by comparing similar sounding utterances using Viterbi alignment and multivariate analysis which maximizes the differences between correct and incorrect recognition multivariate distributions.

Abstract: Speech words are recognized by first recognizing each spectral vector identified by a label (feneme), then identifying the word by matching the string of labels against phones using simplified phone machines based on label and transition probabilities and Merkov chains. In one embodiment, a detailed acoustic match word score is combined with an approximate acoustic match word score to provide a total word score for a subject word. In another embodiment, a polling word score is combined with an acoustic match word score to provide a total word score for a subject word. The acoustic models employed in the acoustic matching may correspond, alternatively, to phonetic elements or to fenemes. Fenemes represent labels generated by an acoustic processor in response to a spoken input. Apparatus and method for determining word scores according to approximate acoustic matching and for determining word scores according to a polling methodology are disclosed.

Abstract: A sequential decoder for error correction on burst and random noise channels using convolutionally encoded data. The decoder interacts with a deinterleaver which time demultiplexes data from a data channel from its time multiplexed form into a predetermined transformed order. The decoder includes a memory for storing a table of likelihood values which are derived from known error statistics about the data channel such as the probabilities of random errors and burst errors, burst error severity and burst duration. The decoder removes an encoded subblock of data from the deinterleaver and enters it into a replica of the convolutional encoder which calculates a syndrome bit from a combination of the presently received subblock together with a given number of previous subblocks. The syndrome bit indicates if the current assumption of the path through the convolutional tree is correct.