Abstract: A method and apparatus for interactive language instruction is provided that displays text files for processing, provide key features and functions for interactive learning, displays facial animation, and provides a workspace for language building functions. The system includes a stored set of language rules as part of the text-to-speech sub-system, as well as another stored set of rules as applied to the process of learning a language. The method implemented by the system includes digitally converting text to audible speech, providing the audible speech to a user or student (with the aid of an animated image in selected circumstances), prompting the student to replicate the audible speech, comparing the student's replication with the audible speech provided by the system, and providing feedback and reinforcement to the student by, for example, selectively recording or playing back the audible speech and the student's replication.

Abstract: A binding box for packaging and paper recycling comprises of a base, four trays, and four supporting parts connecting the trays and base, respectively. Each of the trays holds a corner to a quarter of the area of the papers or materials which need to be bound. The four trays work together to hold papers or any materials that needs to be bound but there is a clearance between any two pairs of the trays. Given the clearance between the trays and the clearance between the base and trays, human hands, ropes, or binding tools can go through to bind the papers without touching any one of the trays or moving the objects which needs to be bound. The ropes are placed in the clearances between trays. Once the binding is finished, a stack of bound papers or materials can be removed directly from the top of the binding box without moving the box.

Abstract: A method and apparatus for performing real-time endpoint detection for use in automatic speech recognition. A filter is applied to the input speech signal and the filter output is then evaluated with use of a state transition diagram (i.e., a finite state machine). The filter is advantageously designed in light of several criteria in order to increase the accuracy and robustness of detection. The state transition diagram advantageously has three states. The endpoints which are detected may then be advantageously applied to the problem of energy normalization of the speech portion of the signal.

Abstract: A method and apparatus for extracting speech features from a speech signal in which the linear frequency spectrum data, as generated, for example, by a conventional frequency transform, is first converted to logarithmic frequency spectrum data having frequency data distributed on a substantially logarithmic (rather than linear) frequency scale. Then, a plurality of digital auditory filters is applied to the resultant logarithmic frequency spectrum data, each of these filters having a substantially similar shape, but centered at different points on the logarithmic frequency scale. Because each of the filters have a similar shape, the feature extraction approach of the present invention advantageously can be easily modified or tuned by adjusting each of the filters in a coordinated manner, with the adjustment of only a handful of filter parameters.

Abstract: Techniques for fast and robust data object classifier training are described. A process of classifier training creates a set of Gaussian mixture models, one model for each class to which data objects are to be assigned. Initial estimates of model parameters are made using training data. The model parameters are then optimized to maximize an aggregate a posteriori probability that data objects in the set of training data will be correctly classified. Optimization of parameters for each model is performed through the process of a number of iterations in which the closed form solutions are computed for the model parameters of each model, the model performance is tested to determine if the newly computed parameters improve the model performance and the model is updated with the newly computed parameters if performance has improved. At each new iteration, the parameters computed in the previous iteration are used as initial estimates.

Abstract: A speaker verification method and apparatus which advantageously minimizes the constraints on the customer and simplifies the system architecture by using a speaker dependent, rather than a speaker independent, background model, thereby obtaining many of the advantages of using a background model in a speaker verification process without many of the disadvantages thereof. In particular, no training data (e.g. speech) from anyone other than the customer is required, no speaker independent models need to be produced, no a priori knowledge of acoustic rules are required, and, no multi-lingual phone models, dictionaries, or letter-to-sound rules are needed. Nonetheless, in accordance with an illustrative embodiment of the present invention, the customer is free to select any password phrase in any language.

Abstract: A method and apparatus for interactive language instruction is provided that displays text files for processing, provide key features and functions for interactive learning, displays facial animation, and provides a workspace for language building functions. The system includes a stored set of language rules as part of the text-to-speech sub-system, as well as another stored set of rules as applied to the process of learning a language. The method implemented by the system includes digitally converting text to audible speech, providing the audible speech to a user or student (with the aid of an animated image in selected circumstances), prompting the student to replicate the audible speech, comparing the student's replication with the audible speech provided by the system, and providing feedback and reinforcement to the student by, for example, selectively recording or playing back the audible speech and the student's replication.

Abstract: A method and apparatus for performing real-time endpoint detection for use in automatic speech recognition. A filter is applied to the input speech signal and the filter output is then evaluated with use of a state transition diagram (i.e., a finite state machine). The filter is advantageously designed in light of several criteria in order to increase the accuracy and robustness of detection. The state transition diagram advantageously has three states. The endpoints which are detected may then be advantageously applied to the problem of energy normalization of the speech portion of the signal.

Abstract: A method and apparatus for extracting speech features from a speech signal in which the linear frequency spectrum data, as generated, for example, by a conventional frequency transform, is first converted to logarithmic frequency spectrum data having frequency data distributed on a substantially logarithmic (rather than linear) frequency scale. Then, a plurality of digital auditory filters is applied to the resultant logarithmic frequency spectrum data, each of these filters having a substantially similar shape, but centered at different points on the logarithmic frequency scale. Because each of the filters have a similar shape, the feature extraction approach of the present invention advantageously can be easily modified or tuned by adjusting each of the filters in a coordinated manner, with the adjustment of only a handful of filter parameters.

Abstract: A method and an apparatus for performing stochastic matching of a set of input test speech data with a corresponding set of training speech data. In particular, a set of input test speech feature information, having been generated from an input test speech utterance, is transformed so that the stochastic characteristics thereof more closely match the stochastic characteristics of a corresponding set of training speech feature information. The corresponding set of training speech data may, for example, comprise training data which was generated from a speaker having the claimed identity of the speaker of the input test speech utterance. Specifically, in accordance with the present invention, a first covariance matrix representative of stochastic characteristics of input test speech feature information is generated based on the input test speech feature information.