Abstract: Systems, devices, media, and methods are presented for determining a level of abusive network behavior suspicion for groups of entities and for identifying suspicious entity groups. A suspiciousness metric is developed and used to evaluate a multi-view graph across multiple views where entities are associated with nodes of the graph and attributes of the entities are associated with levels of the graph.

Abstract: Abstracting data that originates from different sensors and transducers using artificial neural networks. A method can include identifying topological patterns of activity in a recurrent artificial neural network and outputting a collection of digits. The topological patterns are responsive to an input, into the recurrent artificial neural network, of first data originating from a first sensor and second data originating from a second sensor. Each topological pattern abstracts a characteristic shared by the first data and the second data. The first and second sensors sense different data. Each digit represents whether one of the topological patterns of activity has been identified in the artificial neural network.

Abstract: A computing device receives a data X and Y, each having N samples. A function f(x,y) is defined to be a trainable neural network based on the data X and the data Y. A permuted version of the data Y is created. A loss mean is computed based on the trainable neural network f(x,y), the permuted version of the sample data Y, and a trainable scalar variable ?. A loss with respect to the scalar variable ? and the trainable neural network is minimized. Upon determining that the loss is at or below the predetermined threshold, estimating a mutual information (MI) between a test data XT and YT. If the estimated MI is above a predetermined threshold, the test data XT and YT is deemed to be dependent. Otherwise, it is deemed to be independent.

Abstract: Providing knowledge representation of material content being consumed by a user combines the user's current behavioral data and data from external sources such as internet web sites and social media network. Visual representations of entities and their relationships in the content being consumed by the user are created while the user is consuming content, and displayed via a graphical user interface.

Abstract: A method of detecting tampering in a compressed digital image includes extracting one or more neighboring joint density features from a digital image under scrutiny and extracting one or more neighboring joint density features from an original digital image. The digital image under scrutiny and the original digital image are decompressed into a spatial domain. Tampering in the digital image under scrutiny is detected based on at least one difference in a neighboring joint density feature of the digital image under scrutiny and a neighboring joint density feature of the original image. In some embodiments, detecting tampering in the digital image under scrutiny includes detecting down-recompression of at least a portion of the digital image. In some embodiments, detecting tampering in the digital image includes detecting inpainting forgery in the same quantization.

Abstract: A speech recognition method, comprising: receiving a speech input in a first noise environment which comprises a sequence of observations; determining the likelihood of a sequence of words arising from the sequence of observations using an acoustic model, comprising: providing an acoustic model for performing speech recognition on a input signal which comprises a sequence of observations, wherein said model has been trained to recognise speech in a second noise environment, said model having a plurality of model parameters relating to the probability distribution of a word or part thereof being related to an observation; adapting the model trained in the second environment to that of the first environment; the speech recognition method further comprising determining the likelihood of a sequence of observations occurring in a given language using a language model; combining the likelihoods determined by the acoustic model and the language model and outputting a sequence of words identified from said spee

Abstract: Technologies are described herein for noise adaptive training to achieve robust automatic speech recognition. Through the use of these technologies, a noise adaptive training (NAT) approach may use both clean and corrupted speech for training. The NAT approach may normalize the environmental distortion as part of the model training. A set of underlying “pseudo-clean” model parameters may be estimated directly. This may be done without point estimation of clean speech features as an intermediate step. The pseudo-clean model parameters learned from the NAT technique may be used with a Vector Taylor Series (VTS) adaptation. Such adaptation may support decoding noisy utterances during the operating phase of a automatic voice recognition system.

Abstract: A rope-jumping algorithm is employed in a Hidden Markov Model based text to speech system to determine start and end models and to modify the start and end models by setting small co-variances. Disordered acoustic parameters due to violation of parameter constraints are avoided through the modification and result in stable line frequency spectrum for the generated speech.

Abstract: A speech recognition method includes receiving a speech input signal in a first noise environment which includes a sequence of observations, determining the likelihood of a sequence of words arising from the sequence of observations using an acoustic model, adapting the model trained in a second noise environment to that of the first environment, wherein adapting the model trained in the second environment to that of the first environment includes using second order or higher order Taylor expansion coefficients derived for a group of probability distributions and the same expansion coefficient is used for the whole group.

Abstract: An object comparison method comprises: generating a first ordered vector sequence representation of a first object; generating a second ordered vector sequence representation of a second object; representing the first object by a first ordered sequence of model parameters generated by modeling the first ordered vector sequence representation using a semi-continuous hidden Markov model employing a universal basis; representing the second object by a second ordered sequence of model parameters generated by modeling the second ordered vector sequence representation using a semi-continuous hidden Markov model employing the universal basis; and comparing the first and second ordered sequences of model parameters to generate a quantitative comparison measure.

Abstract: The technology disclosed relates to a system and method for fast, accurate and parallelizable speech search, called Crystal Decoder. It is particularly useful for search applications, as opposed to dictation. It can achieve both speed and accuracy, without sacrificing one for the other. It can search different variations of records in the reference database without a significant increase in elapsed processing time. Even the main decoding part can be parallelized as the number of words increase to maintain a fast response time.