摘要:
A set of data objects is identified satisfying a search query associated with an application adapted to perform a set of transactions on the data objects. A plurality of common attributes are identified, each shared by at least two objects in the set of data objects. A graphical analytics viewer is dynamically selected from a plurality of viewers each adapted to present a representation of data objects according to a corresponding analytics scheme. The selected viewer is selected for presentation in a graphical user interface based on identifying that the viewer has an analytics scheme related to one of the common attributes. Presentation of the selected viewer includes a selectable graphical representation of each data object in the set of data objects. At least one of the graphical representations is selected and a transaction from the set of transactions initiated on the data object corresponding to the selected graphical representation.
摘要:
At least one analytical operation from a set of different analytical operations may be determined based on at least one input. The input(s) may comprise contextual information of working content being displayed to a user on a device and comprising numerical data. Supplemental information for the working content may be generated using the determined analytical operation(s), may comprise a numerical-based analysis of the numerical data, and may be caused to be displayed to the user concurrently with the working content. The contextual information may comprise structured data. The input(s) may further comprise at least one of a history of the user's interactions with the working content, a history of the user's interactions with recommendations of supplemental information for the working content, a history of other users' interactions with the working content, and a history of other users' interactions with recommendations of supplemental information for the working content.
摘要:
At least one analytical operation from a set of different analytical operations may be determined based on at least one input. The input(s) may comprise contextual information of working content being displayed to a user on a device and comprising numerical data. Supplemental information for the working content may be generated using the determined analytical operation(s), may comprise a numerical-based analysis of the numerical data, and may be caused to be displayed to the user concurrently with the working content. The contextual information may comprise structured data. The input(s) may further comprise at least one of a history of the user's interactions with the working content, a history of the user's interactions with recommendations of supplemental information for the working content, a history of other users' interactions with the working content, and a history of other users' interactions with recommendations of supplemental information for the working content.
摘要:
Methods and systems are provided for remote tuning and debugging of an automatic speech recognition system. Trace files are generated on-site from input speech by efficient, lossless compression of MFCC data, which is merged with compressed pitch and voicing information and stored as trace files. The trace files are transferred to a remote site where human-intelligible speech is reconstructed and analyzed. Based on the analysis, parameters of the automatic speech recognition system are remotely adjusted.
摘要:
A method for processing a speech signal includes dividing the speech signal into a succession of frames, identifying one or more of the frames as click frames, and extracting phase information from the click frames. The speech signal is encoded using the phase information. Methods are also provided for modeling phase spectra of voiced frames and click frames.
摘要:
An embodiment according to the invention provides a capability of automatically predicting how favorable a given speech signal is for statistical modeling, which is advantageous in a variety of different contexts. In Multi-Form Segment (MFS) synthesis, for example, an embodiment according to the invention uses prediction capability to provide an automatic acoustic driven template versus model decision maker with an output quality that is high, stable and depends gradually on the system footprint. In speaker selection for a statistical Text-to-Speech synthesis (TTS) system build, as another example context, an embodiment according to the invention enables a fast selection of the most appropriate speaker among several available ones for the full voice dataset recording and preparation, based on a small amount of recorded speech material.
摘要:
A method for processing a speech signal includes dividing the speech signal into a succession of frames, identifying one or more of the frames as click frames, and extracting phase information from the click frames. The speech signal is encoded using the phase information. Methods are also provided for modeling phase spectra of voiced frames and click frames.
摘要:
A method for estimating high-order Mel Frequency Cepstral Coefficients, the method comprising initializing any of N−L high-order coefficients (HOC) of an MFCC vector of length N having L low-order coefficients (LOC) to a predetermined value, thereby forming a candidate MFCC vector, synthesizing a speech signal frame from the candidate MFCC vector and a pitch value, and computing an N-dimensional MFCC vector from the synthesized frame, thereby producing an output MFCC vector.
摘要:
A method for compressing a digitized image of a document using optical character recognition (OCR). The method includes performing optical character recognition (OCR) on the digitized image, identifying, based, at least in part, on a result of the performing step, a plurality of classes of characters comprised in the image, each the class of characters having an associated character value and comprising at least one character, pruning each class of characters, thereby producing information describing the plurality of classes of characters and a residual image, and utilizing the information describing the plurality of classes of characters and the residual image as a compressed digitized image in further processing. Related methods and apparatus are also disclosed.
摘要:
A method, system and computer program product are provided for enhancement of speech synthesized by a statistical text-to-speech (TTS) system employing a parametric representation of speech in a space of acoustic feature vectors. The method includes: defining a parametric family of corrective transformations operating in the space of the acoustic feature vectors and dependent on a set of enhancing parameters; and defining a distortion indictor of a feature vector or a plurality of feature vectors. The method further includes: receiving a feature vector output by the system; and generating an instance of the corrective transformation by: calculating a reference value of the distortion indicator attributed to a statistical model of the phonetic unit emitting the feature vector; calculating an actual value of the distortion indicator attributed to feature vectors emitted by the statistical model of the phonetic unit emitting the feature vector; calculating the enhancing parameter values depending on the reference value of the distortion indicator, the actual value of the distortion indicator and the parametric corrective transformation; and deriving an instance of the corrective transformation corresponding to the enhancing parameter values from the parametric family of the corrective transformations. The instance of the corrective transformation may be applied to the feature vector to provide an enhanced feature vector.