Raytheon Bbn Technologies Corp.

Verizon Services Corporation

Verizon Corporate Services Group Inc.

Bbn Technologies Corporation

Premkumar Natarajan

Rohit Prasad

Pradeep Natarajan

Shiv N Vitaladevuni

Douglas Reynold Jones

John Herman Wurster

Stephen Paul Brennan

Gregory Wayne Cermak

Shuang Wu

Alex E Tserkovny

Daniel Joseph McCarthy

Bernadette Anita Nelson

Sandra Kelly Teare

Krishnakumar Subramanian

Linda Louise Witham

Anne M Kraus-Keenan

Elizabeth I Van Horn

Richard Schwartz

Ehry MacRostie

An approach to computation of kernel descriptors is accelerated using precomputed tables. In one aspect, a fast algorithm for kernel descriptor computation that takes O(1) operations per pixel in each patch, based on pre-computed kernel values. This speeds up the kernel descriptor features under consideration, to levels that are comparable with D-SIFT and color SIFT, and two orders of magnitude faster than STIP and HoG3D. In some examples, kernel descriptors are applied to extract gradient, flow and texture based features for video analysis. In tests of the approach on a large database of internet videos used in the TRECVID MED 2011 evaluations, the flow based kernel descriptors are up to two orders of magnitude faster than STIP and HoG3D, and also produce significant performance improvements. Further, using features from multiple color planes produces small but consistent gains.

Fast computation of kernel descriptors

An approach to segmentation or clustering of a set of elements combines separate procedures and uses training data for those procedures on labeled data. This approach is applied to elements being components of an image of text (e.g., printed or handwritten). In some examples, the elements are connected sets of pixels. In images of text, the clusters can correspond to individual lines. The approach provides improved clustering performance as compared to any one of the procedures taken alone.

Segmentation co-clustering

A computationally efficient approach to determining inner products between feature vectors is provided that eliminates or reduces the need for multiplication, and more specifically, provides an efficient and accurate basis selection for techniques such as Orthogonal Matching Pursuit.

Efficient inner product computation for image and video analysis

Distributional information for a set of &#x3b1; vectors is determined using a sparse basis selection approach to representing an input image or video. In some examples, this distributional information is used for a classification task.

Image analysis using coefficient distributions with selective basis feature representation

A method for text recognition includes generating a number of text hypotheses for an image, for example, using an HMM based approach using fixed-width analysis features. For each text hypothesis, one or more segmentations are generated and scored at the segmental level, for example, according to character or character group segments of the text hypothesis. In some embodiments, multiple alternative segmentations are considered for each text hypothesis. In some examples, scores determined in generating the text hypothesis and the segmental score are combined to select an overall text recognition of the image.

Segmental rescoring in text recognition

Disclosed is a method and system for routing telephone calls within a household. In the disclosed home call routing system, a head of the household or other person with administrative authority within the home can control the routing of telephone calls by establishing and modifying call system parameters such as call priorities, traffic times, caller identities, routing rules, etc. through a home computer.

Home call router

Multi-frame persistence of videotext is exploited to mitigate challenges posed by varying characteristics of videotext across frame instances to improve OCR techniques. In some examples, each frame of video is processed to form multiple binary images, and one or more text hypotheses is formed from each binary image. In some examples, one or more combined images are formed from multiple frames processed to form a binary image and a corresponding text hypothesis. The text hypotheses are combined to yield an overall text recognition output.

Multi-frame videotext recognition

A method and apparatus for building a training set for an automated speech recognition-based system, which determines the statistically optimal number of frequently requested responses to automate in order to achieve a desired automation rate. The invention may be used to select the appropriate tokens and responses to train the system and to achieve a desired 'phrase coverage' for all of the many different ways human beings may phrase a request that calls for one of a plurality of frequently-requested responses. The invention also determines the statistically optimal number of tokens (spoken requests) required to train a speech recognition-based system to achieve the desired phrase coverage and optimal allocation of tokens over the set of responses that are to be automated.

Method and apparatus for training an automated speech recognition-based system

A method of training a natural language call routing system using an unsupervised trainer is provided. The unsupervised trainer is adapted to tune performance of the call routing system on the basis of feedback and new topic information. The method of training comprises: storing audio data from an incoming call as well as associated unique identifier information for the incoming call; applying a highly accurate speech recognizer to the audio data from the waveform database to produce a text transcription of the stored audio for the call; forwarding outputs of the second speech recognizer to a training database, the training database being adapted to store text transcripts from the second recognizer with respective unique call identifiers as well as topic data; for a call routed by the call router to an agent: entering a call topic determined by the agent into a form; and supplying the call topic information from the form to the training database together with the associated unique call identifier; and for a call routed to automated fulfillment: querying the caller regarding the true topic of the call; and adding this topic information, together with the associated unique call identifier, to the training database; and performing topic identification model training and statistical grammar model training on the basis of the topic information and transcription information stored in the training database.

Growing community of inventors

Sudbury, MA, United States of America

Premkumar Natarajan