Abstract: An information dissemination system provides users information related to topics extracted from event classes. Event classes can generally be thought of as scripts that specify topics and actions for obtaining information related to the topics. The event classes are executed to obtain information related to the particular event class. The information dissemination system identifies a user event that is of interest to a user. The information dissemination system then identifies an event class that corresponds to the user event. The information dissemination system then performs the actions specified for the event class, obtains the action results, and renders the action results to the user.

Abstract: A framework is provided for obtaining window information. The window information can be applied to different assignment models to assign windows to different groups. A group may correspond to a task being performed by a user. The window information can be semantic or temporal information captured as window events and properties of windows whose events are captured. Temporal information can be information about switches between windows. Semantic information can be window titles. Temporal information, semantic information, or both, can be used to assign windows to groups.

Abstract: The present invention provides systems and methods for signal detection and enhancement. The systems and methods utilize one or more discriminative classifiers (e.g., a logistic regression model and a convolutional neural network) to estimate a posterior probability that indicates whether a desired signal is present in a received signal. The discriminative estimators generate the estimated probability based on one or more signal-to-noise ratio (SNRs) (e.g., a normalized logarithmic posterior SNR (nlpSNR) and a mel-transformed nlpSNR (mel-nlpSNR)) and an estimated noise model. Depending on the resolution desired, the estimated SNR can be generated at a frame level or at an atom level, wherein the atom level estimates are utilized to generate the frame level estimate. The novel systems and methods can be utilized to facilitate speech detection, speech recognition, speech coding, noise adaptation, speech enhancement, microphone arrays and echo-cancellation.

Abstract: Media and system are provided for customizing ads for delivery based on features in a web page. Text in a web page is evaluated to determine the sentiment of the web page. The sentiment can be based on the overall web page or on individual blocks of text within the web page. Based on the sentiment, an ad is created from the text in the web page. The resulting ad is rendered in the web page and shown to a user.

Abstract: An interactive voice advertisement exchange presents an interactive voice advertisement to a user of a voice network who is placed on hold. After the user sends a signal response from a user device to a receiving system and is placed on hold, the hold time and a parameter associated with the signal response are received from the receiving system. Using the hold time and the parameter, an interactive voice advertisement is selected from one or more interactive voice advertisements sent by advertisers. The selected interactive voice advertisement includes a voice message and an application that dictates how the user can interact with the voice message. The voice message and the application of the selected voice interactive voice advertisement are sent to the receiving system. The receiving system sends the voice message to the user device and executes the application during a portion of the hold time.

Abstract: A system that facilitates detecting a targeted topic in a document is described herein. The system includes a receiver component that receives a document. The system additionally includes a topic model component trained using a plurality of training documents including the topic and a plurality of training documents that do not include the topic. The topic model component analyzes the document and automatically determines which portions of the document include the topic and which portions of the document do not include the topic.

Abstract: Embodiments of a computer-implemented advertisement display system are disclosed. In one embodiment, the system includes a speech recognition component that processes a video clip and produces a corresponding collection of speech recognition data indicative of an audio portion of the video clip. The system also includes a collection of advertising material. An advertisement selection component selects an advertisement from the collection of advertising material based on the corresponding collection of speech recognition data. The system also includes a display. An advertisement presentation component displays an indication of the selected advertisement on the display during a simultaneous display of the video clip.

Abstract: Systems and methods are provided for adding an advertisement to a web page by associating advertisements with one or more visual objects e.g., text and/or pictures. Embodiments of the present invention include a method for selecting visual objects and associating the visual object with an advertisement after the web page has been displayed to the user. The visual object may be selected in part based on the user's interactions with the web page. An additional embodiment of the present invention displays the associated advertisement after a user clicks on or hovers over the selected visual object.

Abstract: Signal detectors are described herein. By way of example, a system for detecting signals can include a microphone signal detector, a loudspeaker signal detector, a signal discriminator and a decision component. When the microphone signal detector detects the presence of a microphone signal, the loudspeaker signal detector detects the presence of a loudspeaker signal and the signal discriminator determines that near-end speech dominates loudspeaker echo, the decision component can confirm the presence of doubletalk. When the microphone signal detector detects the presence of a microphone signal and the signal discriminator determines that near-end speech dominates loudspeaker echo, the decision component confirms the presence of near-end signal.

Abstract: The claimed subject matter relates to a system and method that effectuates queryline tracking by constructing and utilizing incremental aspect models that employ probabilistic and/or spectral techniques to discover themes within documents delivered in a stream over time. The system and method upon discovery of a theme or enhancements to already induced or surfaced themes can generate a notification for propagation to a user via one or more user specified communications and/or computing modalities.

Abstract: An information dissemination system provides users information related to topics extracted from event classes. Event classes can generally be thought of as scripts that specify topics and actions for obtaining information related to the topics. The event classes are executed to obtain information related to the particular event class. The information dissemination system identifies a user event that is of interest to a user. The information dissemination system then identifies an event class that corresponds to the user event. The information dissemination system then performs the actions specified for the event class, obtains the action results, and renders the action results to the user.

Abstract: The claimed subject matter relates to an unsupervised incremental learning framework, and in particular, to the creation and utilization of an unsupervised incremental learning framework that facilitates object discovery, clustering, characterization and/or grouping. Such an unsupervised incremental learning framework, once created, can thereafter be employed to incrementally estimate a latent variable model through the utilization of spectral and/or probabilistic models in order to incrementally cluster, discover, group and/or characterize tightly knit themes/topics within document sets and/or streams, thus leading to the generation of a set of themes/topics that better correlate with human perceptual labeling schemes.

Abstract: A framework is provided for obtaining window information. The window information can be applied to different assignment models to assign windows to different groups. A group may correspond to a task being performed by a user. The window information can be semantic or temporal information captured as window events and properties of windows whose events are captured. Temporal information can be information about switches between windows. Semantic information can be window titles. Temporal information, semantic information, or both, can be used to assign windows to groups.

Abstract: Data clustering is performed by executing a spectral technique, embedded within a probabilistic technique. In one embodiment, the probabilistic technique is performed by a generative model, and the spectral technique is performed within the generative model. In another embodiment, the probabilistic technique is performed by an aspect model, and the spectral technique is performed within the aspect model.