Abstract: A language processing system includes a unified language model. The unified language model comprises a plurality of context-free grammars having non-terminal tokens representing semantic or syntactic concepts and terminals, and an N-gram language model having non-terminal tokens. A language processing module capable of receiving an input signal indicative of language accesses the unified language model to recognize the language. The language processing module generates hypotheses for the received language as a function of words of the unified language model and/or provides an output signal indicative of the language and at least some of the semantic or syntactic concepts contained therein.

Abstract: An unsupervised adaptation method and apparatus are provided that reduce the storage and time requirements associated with adaptation. Under the invention, utterances are converted into feature vectors, which are decoded to produce a transcript and alignment unit boundaries for the utterance. Individual alignment units and the feature vectors associated with those alignment units are then provided to an alignment function, which aligns the feature vectors with the states of each alignment unit. Because the alignment is performed within alignment unit boundaries, fewer feature vectors are used and the time for alignment is reduced. After alignment, the feature vector dimensions aligned to a state are added to dimension sums that are kept for that state. After all the states in an utterance have had their sums updated, the speech signal and the alignment units are deleted. Once sufficient frames of data have been received to perform adaptive training, the acoustic model is adapted.

Abstract: A language processing system includes a unified language model. The unified language model comprises a plurality of context-free grammars having non-terminal tokens representing semantic or syntactic concepts and terminals, and an N-gram language model having non-terminal tokens. A language processing module capable of receiving an input signal indicative of language accesses the unified language model to recognize the language. The language processing module generates hypotheses for the received language as a function of words of the unified language model and/or provides an output signal indicative of the language and at least some of the semantic or syntactic concepts contained therein.

Abstract: An unsupervised adaptation method and apparatus are provided that reduce the storage and time requirements associated with adaptation. Under the invention, utterances are converted into feature vectors, which are decoded to produce a transcript and alignment unit boundaries for the utterance. Individual alignment units and the feature vectors associated with those alignment units are then provided to an alignment function, which aligns the feature vectors with the states of each alignment unit. Because the alignment is performed within alignment unit boundaries, fewer feature vectors are used and the time for alignment is reduced. After alignment, the feature vector dimensions aligned to a state are added to dimension sums that are kept for that state. After all the states in an utterance have had their sums updated, the speech signal and the alignment units are deleted. Once sufficient frames of data have been received to perform adaptive training, the acoustic model is adapted.

Abstract: A language model is used in a speech recognition system which has access to a first, smaller data store and a second, larger data store. The language model is adapted by formulating an information retrieval query based on information contained in the first data store and querying the second data store. Information retrieved from the second data store is used in adapting the language model. Also, language models are used in retrieving information from the second data store. Language models are built based on information in the first data store, and based on information in the second data store. The perplexity of a document in the second data store is determined, given the first language model, and given the second language model. Relevancy of the document is determined based upon the first and second perplexities. Documents are retrieved which have a relevancy measure that exceeds a threshold level.

Abstract: A method and system for dynamically selecting words for training a speech recognition system. The speech recognition system models each phoneme using a hidden Markov model and represents each word as a sequence of phonemes. The training system ranks each phoneme for each frame according to the probability that the corresponding codeword will be spoken as part of the phoneme. The training system collects spoken utterances for which the corresponding word is known. The training system then aligns the codewords of each utterance with the phoneme that it is recognized to be part of. The training system then calculates an average rank for each phoneme using the aligned codewords for the aligned frames. Finally, the training system selects words for training that contain phonemes with a low rank.

Abstract: A method and system for achieving an improved recognition accuracy in speech recognition systems which utilize continuous density hidden Markov models to represent phonetic units of speech present in spoken speech utterances is provided. An acoustic score which reflects the likelihood that a speech utterance matches a modeled linguistic expression is dependent on the output probability associated with the states of the hidden Markov model. Context-independent and context-dependent continuous density hidden Markov models are generated for each phonetic unit. The output probability associated with a state is determined by weighing the output probabilities of the context-dependent and context-independent states in accordance with a weighting factor. The weighting factor indicates the robustness of the output probability associated with each state of each model, especially in predicting unseen speech utterances.