Abstract: The content of a media program is recognized by analyzing its audio content to extract therefrom prescribed features, which are compared to a database of features associated with identified content. The identity of the content within the database that has features that most closely match the features of the media program being played is supplied as the identity of the program being played. The features are extracted from a frequency domain version of the media program by a) filtering the coefficients to reduce their number, e.g., using triangular filters; b) grouping a number of consecutive outputs of triangular filters into segments; and c) selecting those segments that meet prescribed criteria, such as those segments that have the largest minimum segment energy with prescribed constraints that prevent the segments from being too close to each other. The triangular filters may be log-spaced and their output may be normalized.

Abstract: The content of a media program is recognized by analyzing its audio content to extract therefrom prescribed features, which are compared to a database of features associated with identified content. The identity of the content within the database that has features that most closely match the features of the media program being played is supplied as the identity of the program being played. The features are extracted from a frequency domain version of the media program by a) filtering the coefficients to reduce their number, e.g., using triangular filters; b) grouping a number of consecutive outputs of triangular filters into segments; and c) selecting those segments that meet prescribed criteria, such as those segments that have the largest minimum segment energy with prescribed constraints that prevent the segments from being too close to each other. The triangular filters may be log-spaced and their output may be normalized.

Abstract: The content of a media program is recognized by analyzing its audio content to extract therefrom prescribed features, which are compared to a database of features associated with identified content. The identity of the content within the database that has features that most closely match the features of the media program being played is supplied as the identity of the program being played. The features are extracted from a frequency domain version of the media program by a) filtering the coefficients to reduce their number, e.g., using triangular filters; b) grouping a number of consecutive outputs of triangular filters into segments; and c) selecting those segments that meet prescribed criteria, such as those segments that have the largest minimum segment energy with prescribed constraints that prevent the segments from being too close to each other. The triangular filters may be log-spaced and their output may be normalized.

Abstract: Structured content and associated metadata from the Web are leveraged to provide specific answer string responses to user questions. The structured content can also be indexed at crawl-time to facilitate searching of the content at search-time. Ranking techniques can also be employed to facilitate in providing an optimum answer string and/or a top K list of answer strings for a query. Ranking can be based on trainable algorithms that utilize feature vectors for candidate answer strings. In one instance, at crawl-time, structured content is indexed and automatically associated with metadata relating to the structured content and the source web page. At search-time, candidate indexed structured content is then utilized to extract an appropriate answer string in response to a user query.

Abstract: A unique system and method that facilitates improving the ranking of items is provided. The system and method involve re-ranking decreasing subsets of high ranked items in separate stages. In particular, a basic ranking component can rank a set of items. A subset of the top or high ranking items can be taken and used as a new training set to train a component for improving the ranking among these high ranked documents. This process can be repeated on an arbitrary number of successive high ranked subsets. Thus, high ranked items can be reordered in separate stages by focusing on the higher ranked items to facilitate placing the most relevant items at the top of a search results list.

Abstract: The subject disclosure pertains to systems and methods for facilitating training of machine learning systems utilizing pairwise training. The number of computations required during pairwise training is reduced by grouping the computations. First, a score is generated for each retrieved data item. During processing of the data item pairs, the scores of the data items in the pair are retrieved and used to generate a gradient for each data item. Once all of the pairs have been processed, the gradients for each data item are aggregated and the aggregated gradients are used to update the machine learning system.

Abstract: The subject disclosure pertains to systems and methods for training machine learning systems. Many cost functions are not smooth or differentiable and cannot easily be used during training of a machine learning system. The machine learning system can include a set of estimated gradients based at least in part upon the ranked or sorted results generated by the learning system. The estimated gradients can be selected to reflect the requirements of a cost function and utilized instead of the cost function to determine or modify the parameters of the learning system during training of the learning system.

Abstract: A process for creating segments out of an arbitrary string of handwritten alphanumeric script is described, in which the contours of the image are defined by the path a ball or pointer follows when allowed to roll from the top and bottom of an image, down or up either side. From the contours, the initial image cut points are determined. The pointer is provided with a capability to measure ink density in the nearby pixels. A grey scale threshold control is provided which operates in conjunction with the pointer as it rolls or moves, to define ink density above the threshold as a white pixel wherein no image content is present; and ink density below the threshold as a black pixel wherein image content is present.

Abstract: Apparatus and processes are described for the automatic recognition of alphanumeric images. A set of cuts are made to the image which include incorrect segmentations. The resulting "cells" comprising in their totality the created segments of the image are then analyzed to determine which cells are legal neighbors and which are not. All cells which are legal neighbors are then presented as connected nodes. A pruning of nodes which are related to certain predetermined image cuts is effected. Each set of remaining connected nodes is then presented to a recognizer which identifies the image and assigns a specified probability to the output. Many cells which are not legal neighbors are thereby not presented to the recognizer, thus saving substantially on computations per recognized image.