Abstract: A multimodal speech-to-speech language translation system and method for translating a natural language sentence of a source language into a symbolic representation and/or target language is provided. The system includes an input device for inputting a natural language sentence of a source language into the system; a translator for receiving the natural language sentence in machine-readable form and translating the natural language sentence into a symbolic representation and/or a target language; and an image display for displaying the symbolic representation of the natural language sentence. Additionally, the image display indicates a correlation between text of the target language, the symbolic representation and the text of the source language.

Abstract: In general, the present invention determines and applies weights for class pairs. The weights are selected to better separate, in reduced-dimensional class space, the classes that are confusable in normal-dimensional class space. During the dimension-reducing process, higher weights are preferably assigned to more confusable class pairs while lower weights are assigned to less confusable class pairs. As compared to unweighted Linear Discriminant Analysis (LDA), the present invention will result in decreased confusability of class pairs in reduced-dimensional class space. The weights can be assigned through a monotonically decreasing function of distance, which assigns lower weights to class pairs that are separated by larger distances. Additionally, weights may also be assigned through a monotonically increasing function of confusability, in which higher weights would be assigned to class pairs that are more confusable.

Abstract: Techniques for providing an automated conversational name dialing system for placing a call in response to an input by a user. One technique begins with the step of analyzing an input from a user, wherein the input includes information directed to identifying an intended recipient of a telephone call from the user. At least one candidate for the intended recipient is identified in response to the input, wherein the at least one candidate represents at least one potential match between the intended recipient and a predetermined vocabulary. A confidence measure indicative of a likelihood that the at least one candidate is the intended recipient is determined, and additional information is obtained from the user to increase the likelihood that the at least one candidate is the intended recipient, based on the determined confidence measure.

Abstract: In order to achieve low error rates in a speech recognition system, for example, in a system employing rank-based decoding, we discriminate the most confusable incorrect leaves from the correct leaf by lowering their ranks. That is, we increase the likelihood of the correct leaf of a frame, while decreasing the likelihoods of the confusable leaves. In order to do this, we use the auxiliary information from the prediction of the neighboring frames to augment the likelihood computation of the current frame. We then use the residual errors in the predictions of neighboring frames to discriminate between the correct (best) and incorrect leaves of a given frame. We present a new methodology that incorporates prediction error likelihoods into the overall likelihood computation to improve the rank position of the correct leaf.

Abstract: In general, the present invention determines and applies weights for class pairs. The weights are selected to better separate, in reduced-dimensional class space, the classes that are confusable in normal-dimensional class space. During the dimension-reducing process, higher weights are preferably assigned to more confusable class pairs while lower weights are assigned to less confusable class pairs. As compared to unweighted Linear Discriminant Analysis (LDA), the present invention will result in decreased confusability of class pairs in reduced-dimensional class space. The weights can be assigned through a monotonically decreasing function of distance, which assigns lower weights to class pairs that are separated by larger distances. Additionally, weights may also be assigned through a monotonically increasing function of confusability, in which higher weights would be assigned to class pairs that are more confusable.

Abstract: A method of speech recognition, in accordance with the present invention includes the steps of grouping acoustics to form classes based on acoustic features, clustering training speakers by the classes to provide class-specific cluster systems, selecting from the cluster systems, a subset of cluster systems closest to adaptation data from a test speaker, transforming the subset of cluster systems to bring the subset of cluster systems closer to the test speaker based on the adaptation data to form adapted cluster systems and combining the adapted cluster systems to create a speaker adapted system for decoding speech from the test speaker. System and methods for building speech recognition systems as well as adapting speaker systems for class-specific speaker clusters are included.