Patent application number | Description | Published |
20110144991 | Compressing Feature Space Transforms - Methods for compressing a transform associated with a feature space are presented. For example, a method for compressing a transform associated with a feature space includes obtaining the transform including a plurality of transform parameters, assigning each of a plurality of quantization levels for the plurality of transform parameters to one of a plurality of quantization values, and assigning each of the plurality of transform parameters to one of the plurality of quantization values to which one of the plurality of quantization levels is assigned. One or more of obtaining the transform, assigning of each of the plurality of quantization levels, and assigning of each of the transform parameters are implemented as instruction code executed on a processor device. Further, a Viterbi algorithm may be employed for use in non-uniform level/value assignments. | 06-16-2011 |
20120150536 | MODEL RESTRUCTURING FOR CLIENT AND SERVER BASED AUTOMATIC SPEECH RECOGNITION - Access is obtained to a large reference acoustic model for automatic speech recognition. The large reference acoustic model has L states modeled by L mixture models, and the large reference acoustic model has N components. A desired number of components N | 06-14-2012 |
20130073276 | MT Based Spoken Dialog Systems Customer/Machine Dialog - Operation of an automated dialog system is described using a source language to conduct a real time human machine dialog process with a human user using a target language. A user query in the target language is received and automatically machine translated into the source language. An automated reply of the dialog process is then delivered to the user in the target language. If the dialog process reaches an initial assistance state, a first human agent using the source language is provided to interact in real time with the user in the target language by machine translation to continue the dialog process. Then if the dialog process reaches a further assistance state, a second human agent using the target language is provided to interact in real time with the user in the target language to continue the dialog process. | 03-21-2013 |
20130268270 | Forced/Predictable Adaptation for Speech Recognition - A method is described for use with automatic speech recognition using discriminative criteria for speaker adaptation. An adaptation evaluation is performed of speech recognition performance data for speech recognition system users. Adaptation candidate users are identified based on the adaptation evaluation for whom an adaptation process is likely to improve system performance. | 10-10-2013 |
20140257809 | SPARSE MAXIMUM A POSTERIORI (MAP) ADAPTION - Techniques disclosed herein include using a Maximum A Posteriori (MAP) adaptation process that imposes sparseness constraints to generate acoustic parameter adaptation data for specific users based on a relatively small set of training data. The resulting acoustic parameter adaptation data identifies changes for a relatively small fraction of acoustic parameters from a baseline acoustic speech model instead of changes to all acoustic parameters. This results in user-specific acoustic parameter adaptation data that is several orders of magnitude smaller than storage amounts otherwise required for a complete acoustic model. This provides customized acoustic speech models that increase recognition accuracy at a fraction of expected data storage requirements. | 09-11-2014 |
20150112669 | REGULARIZED FEATURE SPACE DISCRIMINATION ADAPTATION - A method and apparatus are provided for training a transformation matrix of a feature vector for an acoustic model. The method includes training the transformation matrix of the feature vector. The transformation matrix maximizes an objective function having a regularization term. The method further includes transforming the feature vector using the transformation matrix of the feature vector, and updating the acoustic model stored in a memory device using the transformed feature vector. | 04-23-2015 |
20150161988 | SYSTEMS AND METHODS FOR COMBINING STOCHASTIC AVERAGE GRADIENT AND HESSIAN-FREE OPTIMIZATION FOR SEQUENCE TRAINING OF DEEP NEURAL NETWORKS - A method for training a deep neural network (DNN), comprises receiving and formatting speech data for the training, performing Hessian-free sequence training (HFST) on a first subset of a plurality of subsets of the speech data, and iteratively performing the HFST on successive subsets of the plurality of subsets of the speech data, wherein iteratively performing the HFST comprises reusing information from at least one previous iteration. | 06-11-2015 |
20150310329 | SYSTEMS AND METHODS FOR COMBINING STOCHASTIC AVERAGE GRADIENT AND HESSIAN-FREE OPTIMIZATION FOR SEQUENCE TRAINING OF DEEP NEURAL NETWORKS - A method for training a deep neural network (DNN), comprises receiving and formatting speech data for the training, performing Hessian-free sequence training (HFST) on a first subset of a plurality of subsets of the speech data, and iteratively performing the HFST on successive subsets of the plurality of subsets of the speech data, wherein iteratively performing the HFST comprises reusing information from at least one previous iteration. | 10-29-2015 |