Abstract: An electro-optomechanical beam steering system has: a first deflector for selectively deflecting an optical beam in a first field of regard centered about a boresight; and a rotation stage having a second deflector, the rotation stage selectively positioning the second deflector in azimuth about the boresight, the second deflector selectively deflecting the optical beam of the first field of regard in a second field of regard along a polar axis defined by the second deflector and the azimuth as positioned by the rotation stage. Methods using the beam steering system are also provided, to steer an optical beam or to acquire a target in a field of regard.

Abstract: A switchable apochromatic polarization rotator is provided. A first fixed waveplate has a first principal axis fixed in a first orientation. A second fixed waveplate has a second principal axis fixed in a second orientation. First and second switchable waveplates have principal axes oriented such that broad spectral range electromagnetic radiation transmitted through all of the waveplates has a first rotated polarization, wherein, in response to one or more control signals applied to the switchable waveplates, the principal axes of the switchable waveplates rotate such that the electromagnetic radiation transmitted through all of the waveplates has a second rotated polarization. The switchable waveplates utilize ferroelectric liquid crystal material, nematic liquid crystal material, or be mechanically rotated to adjust for orientation of their principal axes. Utilizing waveplates as described may be used to tune for a desired spectral range and/or compensate for temperature dependencies.

Abstract: A method and apparatus are provided for training parameters in a hidden conditional random field model for use in speech recognition and phonetic classification. The hidden conditional random field model uses parameterized features that are determined from a segment of speech, and those values are used to identify a phonetic unit for the segment of speech. The parameters are updated after processing of individual training samples.

Abstract: A method of modeling a speech recognition system includes decoding a speech signal produced from a training text to produce a sequence of predicted speech units. The training text comprises a sequence of actual speech units that is used with the sequence of predicted speech units to form a confusion model. In further embodiments, the confusion model is used to decode a text to identify an error rate that would be expected if the speech recognition system decoded speech based on the text.

Abstract: A method of modeling a speech recognition system includes decoding a speech signal produced from a training text to produce a sequence of predicted speech units. The training text comprises a sequence of actual speech units that is used with the sequence of predicted speech units to form a confusion model. In further embodiments, the confusion model is used to decode a text to identify an error rate that would be expected if the speech recognition system decoded speech based on the text.

Abstract: A method for creating a language model from a task-independent corpus is provided. In one embodiment, a task dependent unified language model is created. The unified language model includes a plurality of context-free grammars having non-terminals and a hybrid N-gram model having at least some of the same non-terminals embedded therein.

Abstract: The method and apparatus utilize a filter to remove a variety of non-dictated words from data based on probability and improve the effectiveness of creating a language model.

Abstract: In accordance with one embodiment of the present invention, unanticipated semantic intents are discovered in audio data in an unsupervised manner. For instance, the audio acoustics are clustered based on semantic intent and representative acoustics are chosen for each cluster. The human then need only listen to a small number of representative acoustics for each cluster (and possibly only one per cluster) in order to identify the unforeseen semantic intents.

Abstract: A method and apparatus are provided for training and using a hidden conditional random field model for speech recognition and phonetic classification. The hidden conditional random field model uses features, at least one of which is based on a hidden state in a phonetic unit. Values for the features are determined from a segment of speech, and these values are used to identify a phonetic unit for the segment of speech.

Abstract: A method of modeling a speech recognition system includes decoding a speech signal produced from a training text to produce a sequence of predicted speech units. The training text comprises a sequence of actual speech units that is used with the sequence of predicted speech units to form a confusion model. In further embodiments, the confusion model is used to decode a text to identify an error rate that would be expected if the speech recognition system decoded speech based on the text.

Abstract: A method and apparatus are provided for adapting a language model. The method and apparatus provide supervised class-based adaptation of the language model utilizing in-domain semantic information.

Abstract: A method and apparatus are provided for storing parameters of a deleted interpolation language model as parameters of a backoff language model. In particular, the parameters of the deleted interpolation language model are stored in the standard ARPA format. Under one embodiment, the deleted interpolation language model parameters are formed using fractional counts.

Abstract: In a method of entering text into a device a first character input is provided that is indicative of a first character of a text entry. Next, a vocalization of the text entry is captured. A probable word candidate is then identified for a first word of the vocalization based upon the first character input and an analysis of the vocalization. Finally, the probable word candidate is displayed for a user.

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: 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: Methods are disclosed for estimating language models such that the conditional likelihood of a class given a word string, which is very well correlated with classification accuracy, is maximized. The methods comprise tuning statistical language model parameters jointly for all classes such that a classifier discriminates between the correct class and the incorrect ones for a given training sentence or utterance. Specific embodiments of the present invention pertain to implementation of the rational function growth transform in the context of a discriminative training technique for n-gram classifiers.

Abstract: The present invention employs user modeling to model a user's behavior patterns. The user's behavior patterns are then used to influence named entity (NE) recognition.

Abstract: A method of modeling a speech recognition system includes decoding a speech signal produced from a training text to produce a sequence of predicted speech units. The training text comprises a sequence of actual speech units that is used with the sequence of predicted speech units to form a confusion model. In further embodiments, the confusion model is used to decode a text to identify an error rate that would be expected if the speech recognition system decoded speech based on the text.

Abstract: One feature of the present invention uses the parsing capabilities of a structured language model in the information extraction process. During training, the structured language model is first initialized with syntactically annotated training data. The model is then trained by generating parses on semantically annotated training data enforcing annotated constituent boundaries. The syntactic labels in the parse trees generated by the parser are then replaced with joint syntactic and semantic labels. The model is then trained by generating parses on the semantically annotated training data enforcing the semantic tags or labels found in the training data. The trained model can then be used to extract information from test data using the parses generated by the model.