Abstract: A fast, electro-optically switched zoom lens system operates across a broad spectral and thermal range while correcting for birefringent aberrations by means of a polarizing system that preferably includes polarizing reticles.

Abstract: The claimed subject matter provides a system and/or a method that facilitates user selectable advertising networks. Advertising content can be formed into cohesive subsets of advertising. These subsets can be related to criteria to facilitate selection between available subsets of advertising content. A selection component can facilitate selection of the available subsets of advertising content based on these criteria. The criteria can be related to user preferences. Further the criteria can relate to explicit user preferences such as opt-in or opt-out indicia. The user can be presented with more relevant advertising content where user selection of advertising networks occurs.

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.

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.

Abstract: A dual field of view sighting system uses liquid crystals, flip-polarizers and/or flip-mirrors to select between at least two fields of view.

Abstract: Audio/video (A/V) content is analyzed using speech and language analysis components. Metadata is automatically generated based upon the analysis. The metadata is used in generating user interface interaction components which allow a user to view subject matter in various segments of the A/V content and to interact with the A/V content based on the automatically generated metadata.

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 feature functions, at least one of which is based on a hidden state in a phonetic unit. Values for the feature functions are determined from a segment of speech, and these values are used to identify a phonetic unit for the segment of speech.

Abstract: A dual field of view sighting system uses liquid crystals, flip-polarizers and/or flip-mirrors to select between at least two fields of view.

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: 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: 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: A/V content creation, editing and publishing is disclosed. Speech recognition can be performed on the A/V content to identify words therein and form a transcript of the words. The transcript can be aligned with the associated A/V content and displayed to allow selective editing of the transcript and associated A/V content. Keywords and a summary for the transcript can also be identified for use in publishing the A/V content.

Abstract: Audio/video (A/V) content is analyzed using speech and language analysis components. Metadata is automatically generated based upon the analysis. The metadata is used in generating user interface interaction components which allow a user to view subject matter in various segments of the A/V content and to interact with the A/V content based on the automatically generated metadata.

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: 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: 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 fast, electro-optically switched zoom lens system operates across a broad spectral and thermal range while correcting for birefringent aberrations by means of a polarizing system that preferably includes polarizing reticles.

Abstract: A conditional model is used in spoken language understanding. One such model is a conditional random field model.

Abstract: Both speech and alternate modality inputs are used in inputting information spoken into a mobile device. The alternate modality inputs can be used to perform sequential commitment of words in a speech recognition result.