512 results about "Error identification" patented technology

A system and method to improve the automatic adaptation of one or more speech models in automatic speech recognition systems. After a dialog begins, for example, the dialog asks the customer to provide spoken input and it is recorded. If the speech recognizer determines it may not have correctly transcribed the verbal response, i.e., voice input, the invention uses monitoring and if necessary, intervention to guarantee that the next transcription of the verbal response is correct. The dialog asks the customer to repeat his verbal response, which is recorded and a transcription of the input is sent to a human monitor, i.e., agent or operator. If the transcription of the spoken input is correct, the human does not intervene and the transcription remains unmodified. If the transcription of the verbal response is incorrect, the human intervenes and the transcription of the misrecognized word is corrected. In both cases, the dialog asks the customer to confirm the unmodified and corrected transcription. If the customer confirms the unmodified or newly corrected transcription, the dialog continues and the customer does not hang up in frustration because most times only one misrecognition occurred. Finally, the invention uses the first and second customer recording of the misrecognized word or utterance along with the corrected or unmodified transcription to automatically adapt one or more speech models, which improves the performance of the speech recognition system.

In one embodiment, the present invention is a method and apparatus for error correction in speech recognition applications. In one embodiment, a method for recognizing user speech includes receiving a first utterance from the user, receiving a subsequent utterance from the user, and combining acoustic evidence from the first utterance with acoustic evidence from the subsequent utterance in order to recognize the first utterance. It is assumed that, if the first utterance has been incorrectly recognized on a first attempt, the user will repeat the first utterance (or at least the incorrectly recognized portion of the first utterance) in the subsequent utterance.

Hardware-based transactional memory mechanisms, such as Speculative Lock Elision (SLE), may allow multiple threads to concurrently execute critical sections protected by the same lock as speculative transactions. Such transactions may abort due to contention or due to misidentification of code as a critical section. In various embodiments, speculative execution mechanisms may be augmented with software and / or hardware contention management mechanisms to reduce abort rates. Speculative execution hardware may send a hardware interrupt signal to notify software components of a speculative execution event (e.g., abort). Software components may respond by implementing concurrency-throttling mechanisms and / or by determining a mode of execution (e.g., speculative, non-speculative) for a given section and communicating that determination to the hardware speculative execution mechanisms, e.g., by writing it into a lock predictor cache. Subsequently, hardware speculative execution mechanisms may determine a preferred mode of execution for the section by reading the corresponding entry from the lock predictor cache.

A steering control device for a vehicle has a steering assistance means (7) which performs steering assistance processing for driving an actuator (6) so that a vehicle (1) travels along a lane recognized by a lane recognition means (5) from an image acquired by an image acquisition means (4); a side displacement amount calculation means (8) which calculates a displacement amount in the lane width direction between the position of the vehicle (1) and the center of the recognized lane; a complexity calculation means (10) which calculates the complexity of the acquired image; and a steering assistance inhibition means (11) which inhibits, according to the displacement amount in the lane width direction calculated based on the lane recognized from the acquired image at a given time point and the complexity of the acquired image, steering assistance processing based on the lane by the steering assistance means (7). This prevents inappropriate steering control based on an incorrectly recognized lane when performing the steering control of the vehicle so that the vehicle travels along the lane recognized from the road image.

Speech into a telephone is converted from an analog to a digital signal using voice recognition and the output shown as text on a visual display. An error may be identified and a supplementary phrase substituted by speech in correction. Closing of a transmit switch sends the digital signal to a computer having linguistic translation software which translates the message into a second language. The resultant linguistically translated digital signal is converted to analog using speech synthesis and sent via a public exchange telephone line to a receiving user who requires only a conventional telephone to receive the translated message and may respond in the second language. The response is converted to a digital signal using voice recognition and translated into the original language by the linguistic translation software. The linguistically translated response is converted into an analog signal with speech synthesis and heard in the original language by the original transmitting user. Each user may have a graphic display device and the ability to correct errors in voice recognition, translation, or speech synthesis by identifying the same upon the graphic display device which may have a pressure sensitive screen for error identification and for closing the transmit switch. A practical system for addressing the difficulties arising from voice recognition, translation and speech synthesis is provided.

Methods and system to enable a user of an input action recognition text input system to edit any incorrectly recognized text without re-locating the text insertion position to the location of the text to be corrected. The System also automatically maintains correct spacing between textual objects when a textual object is replaced with an object for which automatic spacing is generated in a different manner. The System also enables the graphical presentation of menu choices in a manner that facilitates faster and easier selection of a desired choice by performing a selection gesture requiring less precision than directly contacting the sub-region of the menu associated with the desired choice.

An object sensing apparatus for driver assistance systems in motor vehicles, including at least two sensor systems which measure data concerning the location and / or motion status of objects in the vicinity of the vehicle, and whose detection regions overlap one another, characterized by an error recognition device that checks the data measured by the sensor systems for absence of contradictions, and outputs an error signal upon detection of a contradiction.

A navigation server 1, a map DB 102, a route searching part 104 for searching a guiding route between a departure place and a destination, a shape-simplified road map generating part 106 for generating shape-simplified road map data in which a road shape of the guiding route is simplified, a notice part detecting part 107 for detecting a part of the guiding route as a notice part having a difference grater than a predetermined quantity between the shape of the guiding route in the map data and a shape of the guiding route in the shape-simplified road map data, a notice information generating part 108 for generating, on the basis of the difference at the notice part between the guiding route in the map data and the shape-simplified road map data, a guidance notice information to be supplied to a navigation terminal 2 when a current place reaches the notice part, and a communicating part 110 for transmitting delivery information including the shape-simplified road map data and the guidance notice information are included. This improves a visibility of the guiding route and decrease error recognition of a guiding direction.

Automatically determining image quality of a machine generated image may generate a local saliency map of the image to obtain a set of unsupervised features. The image is run through a trained convolutional neural network (CNN) to extract a set of supervised features from a fully connected layer of the CNN, the image convolved with a set of learned kernels from the CNN to obtain a complementary set of supervised features. The set of unsupervised features and the complementary set of supervised features are combined, and a first decision on gradability of the image is predicted. A second decision on gradability of the image is predicted based on the set of supervised features. Whether the image is gradable is determined based on a weighted combination of the first decision and the second decision.

A storage server stores data in a stripe of a parity group that includes a plurality of data storage devices to store data and a parity storage device to store parity information. The stripe includes a data block from each of the data storage devices and a parity block from the parity storage device. The storage server receives a data access request specifying a data block in the stripe, and a lost write detection module detects an error in the data block. The lost write detection module compares a first storage device signature stored in a metadata field associated with the data block to a second storage device signature stored in a global field of the data storage device containing the data block. If the first storage device signature matches the second storage device signature, the lost write detection module compares a consistency point count stored in the metadata field to a reconstructed consistency point count. If the reconstructed consistency point count is greater than the consistency point count stored in the metadata field, the lost write detection module identifies the error as a lost write error for the data block. Accurately detecting and identifying the location of a lost write allows the storage server to correct the error and provide a user with a complete and accurate set of data.

A Global Navigation Satellite System (GNSS) receiver and associated method capable of tracking weak GNSS signals from a plurality of GNSS satellites. In a preferred embodiment, code and carrier tracking loops are initially closed around the code phase, carrier frequency, and data bit edge estimates handed over from an acquisition mode. In subsequent tracking, early, prompt, and late copies of the code replica are correlated with the incoming signal. The prompt correlations are coherently integrated over an extended updating interval for data bit edge and sign estimation as well as for carrier phase and frequency error discrimination whereas the early and late correlations are used for code error discrimination. Code delay and carrier phase and frequency errors are used to update the code and carrier tracking loop filters. Together with data bits, they form observables of a GNSS signal's time and frequency parameters for timing and position fixing.

In a pattern identification device performing pattern identification of data which has been input by hierarchically extracting features, a primary feature is extracted and distribution of at least one feature extraction result extracted is analyzed, a secondary feature is extracted according to this analysis result. Thus, it is possible to perform pattern identification robustly against fluctuations of the input pattern at a reduced processing cost while reducing the probability of occurrence of incorrect identification.

A system and methods are provided for operating and building graphically XML processing programs, guiding the user in development of the program, preventing and detecting development errors as the program is being designed, ensuring that the program is valid, i.e. satisfies required input and output constraints at all times, i.e. from the time it is developed to when it is deployed in a production environment, ensuring the automated change management if the internal logic of the Web service, or data sources called by the service or the schema that underlies the Web service are modified. The system includes a graphical XML Programming system where XML processing programs are built and represented in a graphical fashion, a real-time metadata computation and visualization method for each selected execution point in the visual program that provides guided programming, error prevention and detection, and change impact analysis and change management, and, an automated execution path exploration method that enables overall program validation and error identification. The system and methods allow a user to reduce by at least a factor of 2 the costs of development and maintenance of reliable XML processing programs such as Web Services.

Systems and methods of representing and extracting type information from typeless and dynamically-typed programming languages are provided. These systems and methods can be immune to source file edits and the order in which those edits are executed. Deriving type information from these languages allows tools to perform operations, for example, refactoring, intellisense, recognition of semantic errors, etc. These systems and methods can be implemented using processes that, implicitly or explicitly, gather type information for the program, and can also accept user input as well.

The invention discloses a numerical control machine tool translational shaft geometric error measuring device and measuring and identifying method. A laser tracker is used for successively measuring axial feed movements of three fixed points of a single machine tool translational shaft at four different positions, the real-time poses of the translation shaft is calculated by the special continuous moving trajectory of the three fixed points, and errors of a machine tool are identified. Due to the fact the real-time poses of the translation shaft are measured, the acquired machine tool information is much richer than the information acquired by only measuring cutter moving trajectory, and error identification algorithm is quite simple. The method suitable for fast data processing, machine tool error fast compensation and precision detection in the field of machine tools has the advantages of high precision, fast and simple operation, rich measuring information, and the like.

A computer-implemented method and system for validating a task of a plurality of tasks of a project. A computing application executes routines to automatically identify errors associated with one or more tasks. The routines generate exception reports that facilitate correction of the errors via user-determined selections of actions or via corrective actions automatically displayed by the computing application. The error identification facilitates validation of project elements including milestones, dependencies and deliverables, key work products, tasks in a work breakdown structure (WBS), predecessors and successors in the WBS, resources, work and labor rates, links between project plans, and an update of a project. Further, the error identification facilitates an analysis of schedule conflicts between give and get tasks.

Methods and systems are provided for testing and improving the performance of a speech recognition system. Words, phrases or utterances are assembled for recognition by one or more speech recognition engines. At a text-to-speech application, an audio pronunciation of each word, phrase or utterance is created. Each audio pronunciation is passed to one or more speech recognition engines. The speech recognition engine analyzes the audio pronunciations and derives one or more words, phrases or utterances from the audio pronunciations. A confidence score is assigned to each of the one or more words, phrases or utterances derived from the audio pronunciations. If the confidence score for any derived word, phrase or utterance is below an acceptable threshold, the results of the speech recognition engine for the word, phrase or utterance are passed to a developer to allow the developer to take corrective action with respect to the speech recognition engine.

A method or apparatus for error identification of a BCH encoded signal includes processing that begins by receiving a BCH encoded signal in a binary polynomial format to produce a received polynomial. The processing then continues by converting the received polynomial into a plurality of error identifying polynomials. The processing then continues by recursively processing the plurality of binary error identifying polynomials to produce a plurality of error identifying values. The processing then continues by processing the plurality of error identifying values to produce an error locator polynomial that represents error in the received polynomial. The processing then continues by evaluating the error locator polynomial to identify the bit location of the error in the BCH encoded signal. The processing then continues by correcting the BCH encoded signal based on the bit location of the error.

A system and related techniques monitor user navigation behavior to automatically detect candidate sites for addition to a user's browser favorites. A client machine, Internet service provider or other resource may host or execute implicit favorites logic which may detect parameters, behavior and variables indicating that a user may wish to add a Web site or other location or content to their set of browser favorites. Thus for example the navigation to a site a certain number of times a day, week or other period may indicate the user has recurring interest in the content of that site. Other factors, such as dwell time on a Web site or page, repeated click-throughs or selections of a Web site from search results over time, or other behavior or parameters may be captured and analyzed. When a candidate site or other content is identified, the user may be prompted to add that site to their set of browser favorites, or in embodiments may be automatically added according to user or default selection. According to embodiments in another regard, implicit favorites logic may likewise periodically or otherwise be applied to the set of favorites themselves, to for example delete obsolete or other entries. Because potential favorites are automatically sensed and offered for inclusion, users may be less likely to lose track or misidentify Web sites or other content they may later wish to access.

A packet architecture, communication system, and method are provided for determining the location at which a network is disrupted, disabled, and / or severed. The packet can contain control bits and error identification bits which note the location at which disturbance exists, and informs the originating module to take alternative path if necessary. The alternative path can be applied to either re-sending the existing packet or sending future packets between certain modules connected to the network, wherein the network preferably includes one or more ring topologies interconnected with one another between termination devices. The termination devices allow communication across subnets which form an intranet or across a global system, or internet. Although redundant transmission channels are used, each transmission channel preferably does not send redundant packets, nor are the transmission channels dedicated as uni-directional. Instead, each of the redundant transmission channels can send dissimilar packets in a bi-directional fashion.

Disclosed is a numerical control machine tool rotating shaft geometric error three-wire measurement method. High-accuracy calibration of space coordinates of a laser tracker base station can be rapidly finished by the aid of a cat eye and a rotatable cat eye bracket, the influence of a machine tool system error is eliminated by calibration accuracy, rotating movement of three fixed points of a single rotating shaft of a machine tool around an axial line is successively measured at four different measurement positions by the aid of one laser tracker, the cat eye and the rotatable cat eye bracket, real-time poses of the rotating shaft are calculated by the aid of continuous movement tracks of the three fixed points in a space, errors of the rotating shaft of the machine tool are identified, acquired information of the machine tool is rich as the real-time poses of the moving shaft are measured, an error identification algorithm is quite simple and applicable to rapid data processing and rapid compensation of the machine tool errors. The numerical control machine tool rotating shaft geometric error three-wire measurement method has the advantages of low cost, high accuracy, rapidness and simplicity in operation, rich measurement information and the like, and is suitable for accuracy detection in the field of numerical control machine tools.

The invention provides a road traffic sign automatic identification and management system based on deep learning, wherein the system is used for the field of environment perception technology of a smart vehicle. The system comprises a traffic sign acquisition module, a traffic sign identification module and a traffic sign management module. The traffic sign acquisition module acquires a video which comprises the traffic sign and performs matching on each image frame and latitude-and-longitude of equipment in acquiring the image. The traffic sign identification module performs functions of processing the input image, performing positioning detection on the traffic sign, acquiring a candidate area which comprises the traffic sign, and performing classification identification on the traffic sign. The traffic sign management module transmits traffic sign and latitude-and-longitude information to a traffic management department, thereby determining whether placement of the traffic sign is reasonable and performing corresponding adjustment. The road traffic sign automatic identification and management system has advantages of large number of kinds of identified traffic signs, high precision, high real-time performance, etc. The road traffic sign automatic identification and management system further has beneficial effects of reducing effect of factors such as illumination change to image identification, improving interference resistance, and obtaining high identification accuracy and low error identification rate.

The invention discloses a semi-supervised clustering integrated protocol identification method. The method comprises the following steps: various data packets in a network are acquired; received network data is analyzed, and each field of the data packets is extracted and counted; feature code of network data obtained after the network data is analyzed is matched with various feature codes preset in a data base, if the match is successful, the data packets are corresponding protocols; data not successfully matched is subject to cluster analysis, a plurality of base clustering devices are used to cluster the data packets, and the result is fed back, and a priori label value is modified; and a semi-supervised statistical learning is carried out for the result of the clustering of the network data packets and each known protocol, and a discriminant learner is trained. According to the invention, the terminal protocol identification rate is improved, and the amount of calculation is moderate, so that the efficiency is high; one time of dialog generate less flow, inaccurate identification is not easy; and besides, the method integrates a plurality of identification methods, so as to achieve multi-dimension identification. The invention also discloses a corresponding semi-supervised clustering integrated protocol identification system.

The invention discloses a search intention identification method and device. The method comprises the steps that massive historical search statements in the historical search record are obtained and classified, a classification model is built based on the historical search statements, candidate search statements related to the historical search statements are obtained by exploring the classification model, and a special-item search word bank of a preset special-item class is formed by the historical search statements and the candidate search statements corresponding to the same preset special-item class. Compared with white lists, fuzzy search threshold values, pattern matching keywords and the like in the prior art, search statements in the special-item search word bank are more accurate and more comprehensive, the generalization is great, therefore according to the search intention identification method and device, a search intention is identified according to the special-item search word bank, the intention class of a target search statement can be identified more accurately, and the misidentification caused by inconsistency between the manually-specified rule and the actual judgment standard of a user can be avoided.

The invention discloses an anti-counterfeiting fingerprint identification device and an anti-counterfeiting fingerprint identification method. The device is provided with a sense control unit which comprises a CapSenseSigma-Delta (CSD) chip, wherein the CSD sense chip is connected with a conductive film. Fingerprints of living organisms are judged by recording an increment in the CSD sense chip and summating numeric codes converted by a modulator. The fingerprint identification method comprises the following steps in turn: 1) initializing; 2) circuit self-checking; 3) performing a corresponding program according to information input by a user; 4) judging whether to communicate; 5) acquiring image data; and 6) comparing registered users. The device of the invention has low cost, can outputa signal by touching lightly, does not need to adopt any distortion correction optical element, and can reduce manufacturing cost and realize miniaturization; the linear distortion relationship obtained by comparing an acquired fingerprint image with an actual fingerprint image can be corrected by software; and therefore, the device has the advantages of high quality of acquired optical imaging image, high fingerprint identification reliability, low error identification rate, good effect on anti-counterfeiting fingerprints, simple structure and low power consumption.

An imaging apparatus capable of reducing the possibility that shooting images fails, by preventing a subject from going out of the frame, being occluded and being recognized erroneously, and improving the usability of the tracking function. With this imaging apparatus, display information creating section 107 creates display information which calls for attention not to lose the sight of main subject 300 that is being tracked or not to make main subject 300 go out of the frame, and associates the created display information with main subject 300 that is being tracked to display on display screen 200.

A receiver-specific regulation of the transmission energy of a symbol to be transmitted is effected by adaptation of the symbol duration or by adaptation of the number of bits transmitted with the symbol or by both measures in combination, in each case using a respective predetermined transmission power. As a result each of the measures provided for adjustment of the transmission energy effects adaptation of the symbol duration per bit, that is to say the ratio of the symbol duration to the number of bits contained therein. What is crucial for adaptation in each case is observing, or, in an alternative form of the method, falling below an upper limit value in respect of an error recognition rate associated with the respective receiver when using the predetermined transmission power. The transmission method according to the invention therefore, to clearly indicate the distinction from power management methods, can also be referred to as energy management in the form of bit duration management (BDM). That is a significant difference in relation to previously known methods and this signifies a completely new network organization which is referred to as energy budget management.

An identification method and apparatus of confusable character are provided. The method involves: the detected character image is identified to gain the initial character information which is corresponding to the character image; the step change times of the corresponding external outline of the character image are counted if the initial character information is the confusable character; the final character information corresponding to the character image is confirmed according to the step change times; The final character information of the character image can be known conveniently according to the step change times, therefore the corresponding correct character information of the character image can be identified more precisely. The possibility of wrong identification of the character image because of the appearing confusable character can be reduced, and the identification precision rate of the confusable character can be improved.