Abstract:
PROBLEM TO BE SOLVED: To provide a system and a method for speech recognition which includes a semantic language model and a phraseological language model and also includes a unification language model as well. SOLUTION: The system and method include: generating a set of powerful hypotheses for speech recognition; re-scoring the powerful hypotheses by using semantic contents by using a semantic structured language model; and making the recognized speech articulate by using the semantic structured language model and scoring a syntax analysis tree for identifying the best sentence according to the syntax analysis tree of sentences. COPYRIGHT: (C)2005,JPO&NCIPI
Abstract:
PROBLEM TO BE SOLVED: To provide a combination of a log-linear model with a multitude of speech features to recognize unknown speech utterances in a speech recognition system. SOLUTION: The speech recognition system models the posterior probability of linguistic units relevant to speech recognition using the log-linear model. The posterior model captures the probability of the linguistic unit given the observed speech features and the parameters of the posterior model. The posterior model may be determined using the probability of the word sequence hypotheses given a multitude of speech features. Log-linear models are used with features derived from sparse or incomplete data. The speech features that are utilized may include asynchronous, overlapping and statistically non-independent speech features. Not all features used in training need to appear in testing/recognition. COPYRIGHT: (C)2005,JPO&NCIPI
Abstract:
YO987-044 CONSTRUCTING MARKOV MODEL WORD BASEFORMS FROM MULTIPLE UTTERANCES BY CONCATENATING MODEL SEQUENCES FOR WORD SEGMENTS 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.
Abstract:
AUTOMATIC GENERATION OF SIMPLE MARKOV MODEL STUNTED BASEFORMS FOR WORDS IN A VOCABULARY The present invention addresses the problem of automatically constructing a phonetic-type baseform which, for a given word, is stunted in length relative to a fenemic baseform for the given word. Specifically, in a system that (i) defines each word in a vocabulary by a fenemic baseform of fenemic phones, (ii) defines an alphabet of composite phones each of which corresponds to at least one fenemic phone, and (iii) generates a string of fenemes in response to speech input, the present invention provides for converting a word baseform comprised of fenemic phones into a stunted word baseform of composite phones by (a) replacing each fenemic phone in the fenemic phone word baseform by the composite phone corresponding thereto; and (b) merging together at least one pair of adjacent composite phones by a single composite phone where the adverse effect of the merging is below a predefined threshold.
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. The synthesized training vector signals are transformed reference feature vector signals representing the values of features of one or more utterances of one or more speakers in a reference set of speakers. The measured training feature vector signals represent the values of features of one or more utterances of a new speaker/user not in the reference set.
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. A revised hypothesis score for each speech hypothesis in the initial subset comprises an estimate of the closeness of a match between the revised model of the speech hypothesis and the sequence of coded representations of the utterance. The speech hypotheses from the initial subset which have the best revised match scores are stored as a reduced subset. At least one word of one or more of the speech hypotheses in the reduced subset is output as a speech recognition result.
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. A revised hypothesis score for each speech hypothesis in the initial subset comprises an estimate of the closeness of a match between the revised model of the speech hypothesis and the sequence of coded representations of the utterance. The speech hypotheses from the initial subset which have the best revised match scores are stored as a reduced subset. At least one word of one or more of the speech hypotheses in the reduced subset is output as a speech recognition result.
Abstract:
SPEECH RECOGNITION EMPLOYING A SET OF MARKOV MODELS THAT INCLUDES MARKOV MODELS REPRESENTING TRANSITIONS TO AND FROM SILENCE The present invention relates to apparatus and method for constructing word baseforms which can be matched against a string of generated acoustic labels which includes: forming a set of phonetic phone machines, wherein each phone machine has (i) a plurality of states, (ii) a plurality of transitions each of which extends from a state to a state, (iii) a stored probability for each transition, and (iv) stored label output probabilities, each label output probability corresponding to the probability of said each phone machine producing a corresponding label; wherein said set of phonetic machines is formed to include a subset of onset phone machines, the stored probabilities of each onset phone machine corresponding to at least one phonetic element being uttered at the beginning of a speech segment; and wherein said set of phonetic machines is formed to include a subset of trailing phone machines, the stored probabilities of each trailing phone machine corresponding to at least one single phonetic element being uttered at the end of a speech segment. Word baseforms are constructed by concatenating phone machines selected from the set.
Abstract:
An apparatus for generating a set of acoustic prototype signals for encoding speech includes means for storing a training script model comprises a series of word-segment models. Each word-segment model comprises a series of elementary models. Means are 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. Means are 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 means for clustering the feature vector signals into a plurality of clusters. Each feature vector signal in a cluster corresponds to a single elementary model in a single location in a single word-segment model. Each cluster signal has a cluster value equal to an average of the feature values of all feature vectors in the signal. Finally, the apparatus includes means for storing a plurality of prototype vector signals. Each prototype vector signal corresponds to an elementary model, has an identifier, and comprises at least two partition values. The partition values are equal to combinations of the cluster values of one or more cluster signals corresponding to the elementary model.