97 results about "Context independent" patented technology

The speech synthesizer is personalized to sound like or mimic the speech characteristics of an individual speaker. The individual speaker provides a quantity of enrollment data, which can be extracted from a short quantity of speech, and the system modifies the base synthesis parameters to more closely resemble those of the new speaker. More specifically, the synthesis parameters may be decomposed into speaker dependent parameters, such as context-independent parameters, and speaker independent parameters, such as context dependent parameters. The speaker dependent parameters are adapted using enrollment data from the new speaker. After adaptation, the speaker dependent parameters are combined with the speaker independent parameters to provide a set of personalized synthesis parameters. To adapt the parameters with a small amount of enrollment data, an eigenspace is constructed and used to constrain the position of the new speaker so that context independent parameters not provided by the new speaker may be estimated.

A discriminative grammar framework utilizing a machine learning algorithm is employed to facilitate in learning scoring functions for parsing of unstructured information. The framework includes a discriminative context free grammar that is trained based on features of an example input. The flexibility of the framework allows information features and/or features output by arbitrary processes to be utilized as the example input as well. Myopic inside scoring is circumvented in the parsing process because contextual information is utilized to facilitate scoring function training.

A method and system for use in a natural language understanding system for including grammars within a statistical parser. The method involves a series of steps. The invention receives a text input. The invention applies a first context free grammar to the text input to determine substrings and corresponding parse trees, wherein the substrings and corresponding parse trees further correspond to the first context free grammar. Additionally, the invention can examine each possible substring using an inventory of queries corresponding to the CFG.

A storage system includes a storage operating system configured to provide two-step data deduplication in which, during a data storage operation and prior to committing data to a storage medium of the storage system, context-aware data deduplication is performed on the data to obtain context-aware deduplicated data, and, subsequent to committing the context-aware deduplicated data to the storage medium, a context-independent data deduplication operation is performed on the context-aware deduplicated data to obtain context-independent deduplicated context-aware deduplicated data, for commitment to the storage medium.

A system for a context-independent framework for management and execution of XML processing tasks is provided. The XML processing tasks are executed by a module, herein referred to as the XSA Engine, according to a predefined set of instructions provided as electronic documents written in a special purpose, XML-based, programming language. The instruction sets contain references to, and control the execution of, instances of three classes of processing modules, which independently accomplish an XML processing subtask and jointly accomplish an XML processing task. The framework is decoupled from any specific execution context, meaning that standardized XML processing can be applied in almost any desired application. The special purpose programming language enhances productivity for development of XML processing tasks as compared to using general purpose programming languages, and diminishes the need for writing custom code to link different types of XML processing subtasks to accomplish an XML processing task.

The present invention is a method and apparatus for compressing and decompressing data. In particular, the present invention provides for (de-)compressing naturalistic color-image and moving-image data, including high-precision and high-definition formats, with zero information loss, one-sample latency and in faster than real time on common computing platforms, resulting in doubled transmission, storage, and playback speed and doubled transmission bandwidth and storage capacity, and hence in doubled throughput for non-CPU-bound image-editing tasks in comparison with uncompressed formats. The present invention uses a nearly symmetrical compression-decompression scheme that provides temporal, spatial, and spectral compression, using a reversible condensing/decondensing filter, context reducer, and encoder/decoder. In the preferred embodiment of the invention, the compression filter is implemented as a cascade of quasilinear feedforward filters, with temporal, multidimensional spatial, and spectral stages, where appropriate, in that order, whose support consists of adjacent causal samples of the respective image. The decompressor cascades quasilinear feedback inverse filters in the reverse order. The filters can be implemented with mere integer addition, subtraction, and either one-dimensional table lookup or constant multiplication and binary shifting, depending on the computing environment Tables permit the data precision to be constrained throughout to that of the image samples. The encoder uses a table of prefix codes roughly inversely proportional in length to their probability, while the decoder uses chunked decode tables for accelerated lookup. In the fastest and simplest mode, the code tables are context-independent. For greater power, at the cost of a reduction in speed, the code tables are based on the temporal, multidimensional spatial, and spectral adjacent causal residue samples, where contexts with similar probability distributions are incoherently collapsed by a context reducer using one-dimensional lookup tables followed by implicitly multidimensional lookup tables, to minimize the overall table size. The invention's minimal resource requirements makes it ideal for implementation in either hardware or software.

A query interpretation method and system uses a combination of context-independent and contextual evaluation to compute interpretations for multiple-term queries. The present invention can be used to search a collection of items, each of which is associated with one or more terms. In certain embodiments, query interpretation involves generating several candidate multiple-term interpretations and scoring them to select one or more interpretations. In certain embodiments, query interpretation involves identifying single-term interpretations for the terms in the query, determining context-independent scores for those single-term interpretations, pruning candidate single-term interpretations, identifying a plurality of candidate multiple-term interpretations, determining a contextual score for each candidate multiple-term interpretation, which may involve using different semantic approaches, and generating one or more multiple-term interpretations that are optimal with respect to a combination of the context-independent and contextual scoring functions.

The present invention allows users to navigate in a Web application or Web pages using a combination of point-and-click and voice-input. At each point of the dialog, the user can use the standard point-and-click interface to perform context-dependent actions, or alternatively, use speech input to navigate and operate in the global application context. The voice input uses a voice navigation component which builds an interface to the installed recognition and synthesis engines. The point-and-click and the voice navigation components can be loaded automatically with the initial Web page of a Web application. Grammars for recognizing vocabulary related to that Web application will be provided with the voice navigation component. The present invention combines the advantages of a context-dependent point-and-click user interface with those of a context-independent speech-input interface. Accordingly, a multi-modal interface can be provided to a Web browser.

A small intelligent device has a memory that stores a finite state automaton, an input/output interface that receives an input and provides an output, and a processor. The processor is arranged to receive the input and to traverse the finite state automaton stored in the memory in order to supply the output to the input/output interface. The automaton may be an embodiment of context sensitive and context independent rules that are enforced by the automaton execution logic.

A computer system for parsing bulk message information into intelligent question retrieval models receives text-based data associated with a particular user. The system encodes the word into a context-dependent vector, wherein the context-dependent vector indicates the meaning of the word across a semantic space. The system also identifies within a context-independent database a context-independent vector that is associated with the word. Further, the system generates an objective output by combining the context-dependent vector and the context-independent vector. Further still, the system generates a sentence encoding representation by processing at least a portion of the text-based data through a high-level feature embedded convolutional semantic model to generate numerical representations of questions and answers within the text-based dataset. The sentence encoding representation is generated at least in part based upon the objective output.

A method and apparatus to use semantic inference with speech recognition systems includes recognizing at least one spoken word, processing the spoken word using a context-free grammar, deriving an output from the context-free grammar, and translating the output to a predetermined command.

The embodiments of the present invention disclose an event detection method and device. The method includes: predefining event-based detection rules with a predicative context-free grammar; generating by parsing the detection rules a parsing table of pushdown automaton which supports parallel parsing; receiving an event to be detected; and analyzing by a controller the event to be detected according to the parsing table, to obtain a detection result. The present invention is especially applicable to detection of network attack events. The embodiments of the present invention detect the attacks with a predicative context-free grammar on the basis of events, and ensure a close combination of a protocol parsing process and an attack detection process, as well as a close combination of multiple attack detection rules, thus decreasing unnecessary calculations. In addition, with an optimized parallel pushdown automaton, the embodiments of the present invention can efficiently analyze the predicative context-free grammar. Consequently, besides hierarchical processing capability and state description capability, the embodiments of the present invention deliver high efficiency.

Embodiments of the invention provide a method and device for multilingual hybrid model establishment and data acquisition, and electronic equipment. The method includes determining a modeling unit ofan acoustic model according to a speech unit contained by multilanguage, and establishing the acoustic model based on a deep neural network, wherein the modeling unit is the context free speech unit;obtaining multilingual hybrid speech training data, converting a hybrid speech signal in the multilingual hybrid speech training data into an eigenvector sequence, and converting a hybrid labelling text corresponding to the hybrid speech signal into a hybrid label sequence of the modeling unit based on the acoustic model; training the acoustic model by using the eigenvector sequence and the hybridlabel sequence; obtaining multilingual hybrid corpus data to train a language model; and establishing a multilingual hybrid speech recognition system according to the acoustic model and the languagemodel. According to the embodiments, recognition accuracy of speech data mixing multiple languages can be enhanced.

A computer architecture uses a PushDown Automaton (PDA) and a Context Free Grammar (CFG) to process data. A PDA engine maintains semantic states that correspond to semantic elements in an input data set. The PDA engine does not have to maintain a new state for each new character in a target search string and typically only transitions to a new state when the entire semantic element is detected. The PDA engine can therefore use a smaller and more predictable state table than DFA algorithms. Transitions between the semantic states are managed using a stack that allows multiple semantic states to be represented by a single nested non-terminal symbol.

A system and method to increase the efficiency and effectiveness of a radiologist. A context manager for managing the display of multi-patient contexts. In an embodiment computer software operates as a context manager and correlates the context of at least one information container with at least one image container. A graphical container displaying information about a patient, as opposed to an image, may be an information container. A graphical container displaying images of a patient, as opposed to information, may be an image container. In order to minimize occurrences of a user viewing information about a first patient and images of a second patient, and mistakenly believing the information and images belong to the same patient, a visual indicator may be displayed over images that are out-of-context with the information displayed. The visual indicator may be a watermark to alert a user of a difference in context.

According to one aspect of the invention, a method is provided in which a set of multiple mixture monophone models is created and trained to generate a set of multiple mixture context dependent models. A set of single mixture triphone models is created and trained to generate a set of context dependent models. Corresponding states of the triphone models are clustered to obtain a set of tied states based on a decision tree clustering process. Parameters of the context dependent models are estimated using a data dependent maximum a posteriori (MAP) adaptation method in which parameters of the tied states of the context dependent models are derived by adapting corresponding parameters of the context independent models using the training data associated with the respective tied states.

This invention relates to a unit selection module for Chinese Text-to-Speech (TTS) synthesis, mainly comprising a probabilistic context free grammar (PCFG) parser, a latent semantic indexing (LSI) module, and a modified variable-length unit selection scheme; any Chinese sentence is firstly input and then parsed into a context-free grammar (CFG) by the PCFG parser; wherein there are several possible CFGs for every Chinese sentence, and the CFG (or the syntactic structure) with the highest probability is then taken as the best CFG (or the syntactic structure) of the Chinese sentence; the LSI module is then used to calculate the structural distance between all the candidate synthesis units and the target unit in a corpus; through the modified variable-length unit selection scheme, tagged with the dynamic programming algorithm, the units are searched to find the best synthesis unit concatenation sequence.

The embodiments of the present invention disclose an event detection method and device. The method includes: predefining event-based detection rules with a predicative context-free grammar; generating by parsing the detection rules a parsing table of pushdown automaton which supports parallel parsing; receiving an event to be detected; and analyzing by a controller the event to be detected according to the parsing table, to obtain a detection result. The present invention is especially applicable to detection of network attack events. The embodiments of the present invention detect the attacks with a predicative context-free grammar on the basis of events, and ensure a close combination of a protocol parsing process and an attack detection process, as well as a close combination of multiple attack detection rules, thus decreasing unnecessary calculations. In addition, with an optimized parallel pushdown automaton, the embodiments of the present invention can efficiently analyze the predicative context-free grammar. Consequently, besides hierarchical processing capability and state description capability, the embodiments of the present invention deliver high efficiency.

A method and system is provided for computing an approximation of the results of a query. The approximation represents a superset of all possible results, by computing a set of records of types (as opposed to a set of records of values, which is the normal result of a query). This is different from conventional systems, which typically infer types for each field individually. For each record of types, one may also keep track of equalities of fields to improve the precision of the approximation. The approximation can be used to detect erroneous parts of queries that always return an empty result, regardless of the contents of the data source. Furthermore, the same approximation is also useful in performing optimizations: first, by eliminating parts of procedure calls that are guaranteed to be irrelevant to the calling context, and second, by eliminating unnecessary type tests in the query.