Abstract: A two-way speech-to-speech (S2S) translation system actively detects a wide variety of common error types and resolves them through user-friendly dialog with the user(s). Examples include features including one or more of detecting out-of-vocabulary (OOV) named entities and terms, sensing ambiguities, homophones, idioms, ill-formed input, etc. and interactive strategies for recovering from such errors. In some examples, different error types are prioritized and systems implementing the approach can include an extensible architecture for implementing these decisions.

Abstract: Features are disclosed for filtering portions of an output audio signal in order to improve automatic speech recognition on an input signal which may include a representation of the output signal. A signal that includes audio content can be received, and a frequency or band of frequencies can be selected to be filtered from the signal. The frequency band may correspond to a desired frequency band for speech recognition. An input signal can be obtained comprising audio data corresponding to a user utterance and presentation of the output signal. Automatic speech recognition can be performed on the input signal. In some cases, an acoustic model trained for use with such frequency band filtering may be used to perform speech recognition.

Abstract: Features are disclosed for detecting words in audio using environmental information and/or contextual information in addition to acoustic features associated with the words to be detected. A detection model can be generated and used to determine whether a particular word, such as a keyword or “wake word,” has been uttered. The detection model can operate on features derived from an audio signal, contextual information associated with generation of the audio signal, and the like. In some embodiments, the detection model can be customized for particular users or groups of users based usage patterns associated with the users.

Abstract: Features are disclosed for estimating a false rejection rate in a detection system. The false rejection rate can be estimated by fitting a model to a distribution of detection confidence scores. An estimated false rejection rate can then be computed for confidence scores that fall below a threshold. The false rejection rate and model can be verified once the detection system has been deployed by obtaining additional data with confidence scores falling below the threshold. Adjustments to the model or other operational parameters can be implemented based on the verified false rejection rate, model, or additional data.

Abstract: Techniques are described for documenting the positions of items in a room, such as in rooms that are configured for testing automated systems that perform position-related functions. A non-contact measuring tool may be placed at different reference positions within the room. At each position, measurements are made to the room corners and to items of interest within the room. Based on this information, coordinates of the reference positions are calculated. Coordinates of the items are calculated based on the determined coordinates of the reference positions.

Abstract: A system to recognize text, objects, or symbols in a captured image using machine learning models reduces computational overhead by generating a plurality of thumbnail versions of the image at different downscaled resolutions and aspect ratios, and then processing the downscaled images instead of the entire image, or sections of the entire image. The downscaled images are processed to produce a combine feature vector characterizing the overall image. The combined feature vector is processed using the machine learning model.

Abstract: Natural language controlled devices may be configured to activate command recognition in response to one or more wake words. Techniques are provided to allow for multiple operating modes in which different recognition parameters are employed in recognizing wake words that activate the natural language control functionality of a computing device.

Abstract: 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.

Abstract: A system estimates text orientation in images captured using a handheld camera prior detecting text in the image. Text orientation is estimated based on edges detected within the image, and the image is rotated based on the estimated orientation. Text detection and processing is then performed on the rotated image. Non-text features along a periphery of the image may be sampled to assure that clutter will not undermine the estimation of orientation.

Abstract: 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.

Abstract: 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.

Abstract: Distributional information for a set of ? 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.

Abstract: A two-way speech-to-speech (S2S) translation system actively detects a wide variety of common error types and resolves them through user-friendly dialog with the user(s). Examples include features including one or more of detecting out-of-vocabulary (OOV) named entities and terms, sensing ambiguities, homophones, idioms, ill-formed input, etc. and interactive strategies for recovering from such errors. In some examples, different error types are prioritized and systems implementing the approach can include an extensible architecture for implementing these decisions.

Abstract: Distributional information for a set of ? 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: A system and method facilitating an end-to-end solution for one or more service offerings. The end-to-end solution includes the modeling, provisioning, and rating of a single subscription as at least one of prepaid and postpaid. The system includes a CRM layer, an integration layer, a rating and billing management layer, and a service activation platform layer.