Abstract: Category context models (64) and a universal context model (62) are generated including sums of soft co-occurrences of pairs of visual words in geometric proximity to each other in training images (50) assigned to each category and assigned to all categories, respectively. Context information (76) about an image to be classified (70) are generated including sums of soft co-occurrences of pairs of visual words in geometric proximity to each other in the image to be classified. For each category (82), a comparison is made of (i) closeness of the context information about the image to be classified with the corresponding category context model and (ii) closeness of the context information about the image to be classified with the universal context model. An image category (92) is assigned to the image to be classified being based on the comparisons.

Abstract: In an image classification system (70), a plurality of generative models (30) correspond to a plurality of image classes. Each generative model embodies a merger of a general visual vocabulary and an image class-specific visual vocabulary. A gradient-based class similarity modeler (40) includes (i) a model fitting data extractor (46) that generates model fitting data of an image (72) respective to each generative model and (ii) a dimensionality enhancer (50) that computes a gradient-based vector representation of the model fitting data with respect to each generative model in a vector space defined by the generative model. An image classifier (76) classifies the image respective to the plurality of image classes based on the gradient-based vector representations of class similarity.

Abstract: A method for processing electronic mail includes computing a probability that a text string in an electronic mail message refers to an attachment as a function of a stored probability value for each of a plurality of sequences of words within the text string. Where the email message lacks an attachment, the method includes prompting a user if the computed probability indicates that the text string refers to an attachment.

Abstract: Generic visual categorization methods complement a general vocabulary with adapted vocabularies that are class specific. Images to be categorized are characterized within different categories through a histogram indicating whether the image is better described by the general vocabulary or the class-specific adapted vocabulary.

Abstract: The speech synthesizer is personalized to sound like or mimic the speech characteristics of an individual speaker. The individual speaker provides a quantity of enrollment data, which can be extracted from a short quantity of speech, and the system modifies the base synthesis parameters to more closely resemble those of the new speaker. More specifically, the synthesis parameters may be decomposed into speaker dependent parameters, such as context-independent parameters, and speaker independent parameters, such as context dependent parameters. The speaker dependent parameters are adapted using enrollment data from the new speaker. After adaptation, the speaker dependent parameters are combined with the speaker independent parameters to provide a set of personalized synthesis parameters.

Abstract: A reduced dimensionality eigenvoice analytical technique is used during training to develop context-dependent acoustic models for allophones. Re-estimation processes are performed to more strongly separate speaker-dependent and speaker-independent components of the speech model. The eigenvoice technique is also used during run time upon the speech of a new speaker. The technique removes individual speaker idiosyncrasies, to produce more universally applicable and robust allophone models. In one embodiment the eigenvoice technique is used to identify the centroid of each speaker, which may then be “subtracted out” of the recognition equation.

Abstract: A reduced dimensionality eigenvoice analytical technique is used during training to develop context-dependent acoustic models for allophones. Re-estimation processes are performed to more strongly separate speaker-dependent and speaker-independent components of the speech model. The eigenvoice technique is also used during run time upon the speech of a new speaker. The technique removes individual speaker idiosyncrasies, to produce more universally applicable and robust allophone models. In one embodiment the eigenvoice technique is used to identify the centroid of each speaker, which may then be “subtracted out” of the recognition equation.

Abstract: The speech synthesizer is personalized to sound like or mimic the speech characteristics of an individual speaker. The individual speaker provides a quantity of enrollment data, which can be extracted from a short quantity of speech, and the system modifies the base synthesis parameters to more closely resemble those of the new speaker. More specifically, the synthesis parameters may be decomposed into speaker dependent parameters, such as context-independent parameters, and speaker independent parameters, such as context dependent parameters. The speaker dependent parameters are adapted using enrollment data from the new speaker. After adaptation, the speaker dependent parameters are combined with the speaker independent parameters to provide a set of personalized synthesis parameters.