765 results about "Language recognition" patented technology

A system, method, and computer program are disclosed for recognizing one or more words not listed in a dictionary database. One or more sequences of characters in the word are checked to determine a probability that the word is valid. A prefix removal process removes any prefixes from a word, and obtains information about the removed prefix. A suffix removal process removes any suffixes from the word, and obtains information about the removed suffix. A root process obtains information about a root word from the dictionary database. A combination process then determines if the prefix, the root, and the suffix can be combined into a valid word as defined by one or more combination rules, obtains one or more of the possible parts of speech of the valid word, and stores the parts of speech with the valid word in the dictionary database.

Techniques for adapting a virtual keyboard for multilingual input are disclosed. By way of example, a method of adapting a virtual keyboard for multilingual input includes the steps of detecting an input language and displaying a virtual keyboard corresponding to the input language upon detection of the input language. The identifying step may include automatic identification of an input language, such as by one or more language recognition modules, or it may include manual selection of an input language and activation of at least one language recognition module operative to recognize at least the input language upon selection of the input language.

A system for supervised automatic code generation and tuning for natural language interaction applications, comprising a build environment comprising a developer user interface, automated coding tools, automated testing tools, and automated optimization tools, and an analytics framework software module. Text samples are imported into the build environment and automated clustering is performed to assign them to a plurality of input groups, each input group comprising a plurality of semantically related inputs. Language recognition rules are generated by automated coding tools. Automated testing tools carry out automated testing of language recognition rules and generate recommendations for tuning language recognition rules. The analytics framework performs analysis of interaction log files to identify problems in a candidate natural language interaction application. Optimizations to the candidate natural language interaction application are carried out and an optimized natural language interaction application is deployed into production and stored in the solution data repository.

A system for supervised automatic code generation and tuning for natural language interaction applications, comprising a build environment comprising a developer user interface, automated coding tools, automated testing tools, and automated optimization tools, and an analytics framework software module. Text samples are imported into the build environment and automated clustering is performed to assign them to a plurality of input groups, each input group comprising a plurality of semantically related inputs. Language recognition rules are generated by automated coding tools. Automated testing tools carry out automated testing of language recognition rules and generate recommendations for tuning language recognition rules. The analytics framework performs analysis of interaction log files to identify problems in a candidate natural language interaction application. Optimizations to the candidate natural language interaction application are carried out and an optimized natural language interaction application is deployed into production and stored in the solution data repository.

Methods and systems for selecting a language for text segmentation are disclosed. In one embodiment, at least a first candidate language and a second candidate language associated with a string of characters are identified, at least a first segmented result associated with the first candidate language and a second segmented result associated with the second candidate language are determined, a first frequency of occurrence for the first segmented result and a second frequency of occurrence for the second segmented result are determined, and an operable language is identified from the first candidate language and the second candidate language based at least in part on the first frequency of occurrence and the second frequency of occurrence.

A sign language recognition apparatus and method is provided for translating hand gestures into speech or written text. The apparatus includes a number of sensors on the hand, arm and shoulder to measure dynamic and static gestures. The sensors are connected to a microprocessor to search a library of gestures and generate output signals that can then be used to produce a synthesized voice or written text. The apparatus includes sensors such as accelerometers on the fingers and thumb and two accelerometers on the back of the hand to detect motion and orientation of the hand. Sensors are also provided on the back of the hand or wrist to detect forearm rotation, an angle sensor to detect flexing of the elbow, two sensors on the upper arm to detect arm elevation and rotation, and a sensor on the upper arm to detect arm twist. The sensors transmit the data to the microprocessor to determine the shape, position and orientation of the hand relative to the body of the user.

A language translation device includes a network transceiver configured to provide communication between first and second communication terminals, a language recognition unit, and a language translation unit. The language recognition unit is configured to receive a signal representing speech and / or text in a first human language from the first communication terminal and map the received signal to intermediate data. The language translation unit is configured to generate a translated signal representing speech and / or text in a second human language, which is different from the first human language, in response to the intermediate data and provide the translated signal to the second communication terminal. The speech and / or text represented by the translated signal has a meaning corresponding to that of the speech and / or text represented by the received signal. Related devices and methods of operation are also discussed.

A method and system for providing automatic translation of an electronic communication from a source language to one or more target languages. A source language is determined using a translation identifier or a language identifier means. A user profile is read to determine the target language. The target language and the source language are compared to determine a required translation.

A voice control method and a mobile terminal apparatus are provided. The mobile terminal apparatus includes a voice receiving module, a voice outputting module, a voice wake-up module and a language recognition module. When the voice wake-up module determined that a first voice signal matches to identification information, the voice receiving module is turned on. When the voice receiving module receives a second voice signal after the first voice signal, the language recognition module parses the second voice signal and obtains a voice recognition result. When the voice recognition result includes an executing request, the language recognition module executes a responding operation, and the voice receiving module is turned off from receiving a third voice signal. When the voice recognition result does not include the executing request, the language recognition module executes a speech conversation mode.

A system for supervised automatic code generation and tuning for natural language interaction applications, comprising a build environment comprising a developer user interface, automated coding tools, automated testing tools, and automated optimization tools, and an analytics framework software module. Text samples are imported into the build environment and automated clustering is performed to assign them to a plurality of input groups, each input group comprising a plurality of semantically related inputs. Language recognition rules are generated by automated coding tools. Automated testing tools carry out automated testing of language recognition rules and generate recommendations for tuning language recognition rules. The analytics framework performs analysis of interaction log files to identify problems in a candidate natural language interaction application. Optimizations to the candidate natural language interaction application are carried out and an optimized natural language interaction application is deployed into production and stored in the solution data repository.

A method and apparatus for dynamically separating and recovering original signal sources by processing a set of mixed received mixtures and convolution of said signals utilizing differential equations and a computer. The system of the invention enables the blind separation and recovery of an unknown number of signals mixed together in dynamically changing interference environments with very minimal assumption on the original signals. The system of this invention has practical applications to nonmultiplexed media sharing, adaptive interferer rejection, acoustic sensors, acoustic diagnostics, medical diagnostics and instrumentation, speech, voice, language recognition and processing, wired and wireless modulated communication signal receivers, and cellular communications.

A sign language recognition apparatus and method is provided for translating hand gestures into speech or written text. The apparatus includes a number of sensors on the hand, arm and shoulder to measure dynamic and static gestures. The sensors are connected to a microprocessor to search a library of gestures and generate output signals that can then be used to produce a synthesized voice or written text. The apparatus includes sensors such as accelerometers on the fingers and thumb and two accelerometers on the back of the hand to detect motion and orientation of the hand. Sensors are also provided on the back of the hand or wrist to detect forearm rotation, an angle sensor to detect flexing of the elbow, two sensors on the upper arm to detect arm elevation and rotation, and a sensor on the upper arm to detect arm twist. The sensors transmit the data to the microprocessor to determine the shape, position and orientation of the hand relative to the body of the user.

A system is provided for comparing an input query with a number of stored annotations to identify information to be retrieved from a database. The comparison technique divides the input query into a number of fixed-size fragments and identifies how many times each of the fragments occurs within each annotation using a dynamic programming matching technique. The frequencies of occurrence of the fragments in both the query and the annotation are then compared to provide a measure of the similarity between the query and the annotation. The information to be retrieved is then determined from the similarity measures obtained for all the annotations.

A sign language recognition apparatus and method is provided for translating hand gestures into speech or written text. The apparatus includes a number of 3-axis accelerometers on fingers and back of the palm to measure dynamic and static gestures, an analog multiplexer and a programmable micro controller to detect hand postures of American Sign Language and send them to a host via serial communication. The sensors are connected to a microprocessor to search a library of gestures and generate output signals that can then be used to produce a synthesized voice or written text. The apparatus includes sensors such as accelerometers on the fingers and thumb and two accelerometers on the back of the hand to detect motion and orientation of the hand. Sensors are also provided on the back of the hand or wrist to detect forearm rotation, an angle sensor to detect flexing of the elbow, two sensors on the upper arm to detect arm elevation and rotation, and a sensor on the upper arm to detect arm twist. The sensors transmit the data to the microprocessor to determine the shape, position and orientation of the hand relative to the body of the user.

A method of language recognition wherein decoding ambiguities are identified and at least partially resolved intermediate to the language decoding procedures to reduce the subsequent number of final decoding alternatives. The user is questioned about identified decoding ambiguities as they are being decoded. There are two language decoding levels: fast match and detailed match. During the fast match decoding level a large potential candidate list is generated, very quickly. Then, during the more comprehensive (and slower) detailed match decoding level, the fast match candidate list is applied to the ambiguity to reduce the potential selections for final recognition. During the detailed match decoding level a unique candidate is selected for decoding. Decoding may be interactive and, as each ambiguity is encountered, recognition suspended to present questions to the user that will discriminate between potential response classes. Thus, recognition performance and accuracy is improved by interrupting recognition, intermediate to the decoding process, and allowing the user to select appropriate response classes to narrow the number of final decoding alternatives.

The invention discloses a smart home voice control system combined with a video channel and a control method thereof. The system comprises a gesture detection module, a human face detection module, a recognition system module, a command judgment module and a command display and confirmation module which are sequentially connected. The recognition system module comprises a lip language part and a voice part, wherein the lip language part comprises a human face tracking and positioning module, a lip language video input module and a lip language recognition module which are sequentially connected; and the voice part comprises a voice input module and a voice recognition module which are sequentially connected. By detecting control gestures and recognizing human faces and lip language information to supplement the recognized voice information, the accuracy of control commands is improved and the feasibility of using voices to control a smart home is increased. The smart home voice control system combined with the video channel has very strong interference resistance, can be widely used for various complex environment modes and is particularly suitable for the situation of high noise because of a great number of people in home environments.

The invention relates to an interactive synchronization translation method for multi-media and multi-language, according to various kinds of particular fields, most commonly used multi-language clause or sentence is divided into language material of various scenes and multi-language and interposed into the language material library and used for reserve through processing based on statistical concept, any sentence is also translated by calling machine translation technology, display screen is divided into two parts by combining the multi-media technology of language recognition, voice speech, handwriting recognition, voice control, touch screen choice, and used for a preferred language and input and read of a second language user, interaction between two kinds of language is achieved and multi-language switch is achieved by using a screen soft keyboard. Translation result can be pronounced, interface is friendly, preparative language training is not needed, the invention is portable, convenient and shortcut, the method is used in a mobile phone, PDA, a notebook PC, a desk PC.

The invention provides an identification verifying system for a living human body for electronic payment, so as to overcome defects existing in the prior art. Through various voice-shape-image biometric feature recognition of face recognition, voice recognition, voiceprint recognition and lip language recognition, whether a user is an operator or not and whether the user is an intelligent living body or not are verified, through a client of the electronic payment and the interactive communication of a server, the feature information of a face, a voice, a voiceprint and a lip language is extracted out from a video and an audio obtained by the client of the electronic payment through the client of the electronic payment, and less data flow is used and transmitted into a server terminal through the Internet so as to perform the feature information of the face, the voice, the voiceprint and the lip language. Direct contact between the identification verifying system and the operator is not needed, whether the user is the operator or not and whether the user is the intelligent living body or not are verified, the identification verifying system is convenient to use, easy to accept by the operator and good in customer experience, and besides, an additional hardware is not needed.

The invention discloses an intelligent customer service response method and system, relates to the technical field of intelligent customer service, and can solve the problems of low response efficiency and poor user experience caused by relying on manual customer service in the prior art. The method comprises the steps of preprocessing the customer service historical chat statements to export customer service corpora, and conducting the word segmentation training on the customer service corpora to obtain a language recognition model; carrying out intention identification on corpora asked by auser to match a corresponding service module, carrying out retrieval analysis in an elasticsearch database corresponding to the service module by utilizing an intention identification result, and summarizing output associated keyword answers to form a pre-selected data set; taking a text formed after word segmentation of the question corpus of the user as an input, and carrying out Elasticsearch retrieval in a pre-selected data set to output candidate keyword answers; converting the segmented keywords and the candidate keyword answers into word vectors respectively, calculating the similaritybetween the segmented keywords and the candidate keyword answers in pairs by using a WMD algorithm, and selecting the keyword answers based on the similarity values to respond to the user.

Occurrences of one or more keywords in audio data are identified using a speech recognizer employing a language model to derive a transcript of the keywords. The transcript is converted into a phoneme sequence. The phonemes of the phoneme sequence are mapped to the audio data to derive a time-aligned phoneme sequence that is searched for occurrences of keyword phoneme sequences corresponding to the phonemes of the keywords. Searching includes computing a confusion matrix. The language model used by the speech recognizer is adapted to keywords by increasing the likelihoods of the keywords in the language model. For each potential occurrences keywords detected, a corresponding subset of the audio data may be played back to an operator to confirm whether the potential occurrences correspond to actual occurrences of the keywords.

This invention opens a method and system of realization of the online advertising,it aims to solve the problem that the network side can not in accordance with the contents of voice to push the advertising issue for the client. The invention includes: A. voice flow through the client side will be transformed into text flow; B. through keyword matching, matching advertising for the described text flow; C. network side will be pushed matching advertisements to the client side for users to browse. This invention system includes: advertising calling module, advertising basement, lexical analysis module, advertising matching module, advertising push module; Aboved system also includes: speech recognition module, whish is used for voice flow gained by advertising calling module transforming into text flow; text flow memory modules for use in storage of text flow of language recognition module output, to prepare for lexical analysis module called. Through the implementation of the invention, we may push corresponding advertising to the client side, basing on the contents of the voice flow between clients altenantly.

In some speech recognition applications, not only the language of the utterance is not known in advance, but also a single utterance may contain words in more than one language. At the same time, it is impractical to build speech recognizers for all expected combinations of languages. Moreover, business needs may require a new combination of languages to be supported in short period of time. The invention addresses this issue by a novel way of combining and controlling the components of the single-language speech recognizers to produce multilingual speech recognition functionality capable of recognizing multilingual utterances at a modest increase of computational complexity.

The invention discloses a language recognition method and device for a text and electronic equipment. The language recognition method for the text comprises the steps of extracting language characteristics from a text to be recognized; taking the extracted language characteristics as an input of a text language classifier generated in advance; and calculating to acquire a language to which the text to be recognized belongs by the text language classifier, wherein the language characteristics comprise at least one of N-element continuous word characteristics, N-element continuous character characteristics and affix characteristics. With the adoption of the method provided by the invention, the correct recognition rate and the robustness of language recognition can be improved; and meanwhile, a training corpus set is only needed to be a historical query set marked with a correct language, more content is not needed to be marked, and thus, an effect of high practicability can be achieved.

Search time is reduced with a search engine that includes a bi-directional inverted index facility which can be accessed with a keyword search in one of a number of languages and provide a listing of documents contained in all of those languages. The keywords in all supported languages are preferably stored in an inverted index lookup table cross referenced to documents in those language containing the keywords. Keywords with the same meaning in different languages are accessible together when that keyword in one of the languages is queried. The search engine containing the table can identify pertinent documents either in a selected language, a second language or in all supported languages, as determined by the user. Information about each document can include not only the identity of the document but also information used in ranking the documents such as the number of times that a keyword appears in that document, and the keywords proximity to other keywords. The use of the inverted index table therefore reduces search time by eliminating the need for translation of keywords, their identification in documents and accumulating of ranking information at search runtime and avoids inaccuracies which may result from full text translations of documents.

The invention relates to a structured query language (SQL) based MapReduce operation generating method and system. The method includes analyzing received SQL sentences to generate an abstract syntax tree, converting the abstract syntax tree into a query plan tree, optimizing the query plan tree, and generating a corresponding MapReduce operation according to the optimized query plan tree. According to the system, an another tool for language recognition (Antlr) is based on to generate the abstract syntax tree (AST) from the SQL sentences, further, the AST is based on to generate a query plan tree, and finally, the MapReduce operation is generated on the basis of the query plan tree; meanwhile, corresponding optimization policies are further provided, so that the generated MapReduce operation has higher execution efficiency.

The invention discloses a method and a device for operating and controlling a virtual center console of a blind-operation-supported automobile by gestures. By the method and the device, a user can conveniently use gestures to perform corresponding operation and control on a center console touch screen during driving without transferring road driving sight line, and by an automobile blind operation function, the shortcoming of searching complex and various mechanical buttons in the conventional driving room to control the conventional automobile is well overcome; and meanwhile, the virtual center console integrates a gesture language library module, a gesture analysis and processing module, a gesture language recognition module, a gesture language library management module, a gesture operation and control execution module and a gesture operation and control security mechanism management module, and because of cooperative work of the modules, gesture language operation and control has the characteristics that the gesture language operation and control is easy and convenient to use, gesture operation and control windows are independent, gesture language meaning is unique, a gesture language can be modified, an operation and control mechanism is safe and the like, and convenient, rapid, friendly and safe operation and control experiences of the automobile center console can be brought to the user according to specific requirements.

The invention discloses a lip language recognition method and device, computer equipment and a storage medium. The lip language recognition method comprises the following steps: carrying out standardization processing on a frame rate of an obtained original video, and separating the obtained standard video to obtain an effective audio stream and an effective video stream; tracking a human face in the effective video stream by using a human face recognition algorithm, extracting a mouth area in the human face, and obtaining a frame lip action video so as to obtain a lip image sequence; segmenting the lip image sequence by adopting a sequence segmentation rule to obtain a segmented image sequence; sequentially inputting the segmented image sequences corresponding to the lip image sequences into a lip image recognition model for recognition, and obtaining a lip image recognition result; inputting the effective audio stream into a speech recognition model to obtain a speech recognition result; and when the similarity between the lip image recognition result and the original video reaches a preset value, taking the lip image recognition result as a lip language recognition result of the original video so as to ensure the accuracy of the lip image recognition result.

Disclosed are computer-implemented methods and systems for dynamic selection of speech recognition systems for the use in Chat Information Systems (CIS) based on multiple criteria and context of human-machine interaction. Specifically, once a first user audio input is received, it is analyzed so as to locate specific triggers, determine the context of the interaction or predict the subsequent user audio inputs. Based on at least one of these criteria, one of a free-diction recognizer, pattern-based recognizer, address book based recognizer or dynamically created recognizer is selected for recognizing the subsequent user audio input. The methods described herein increase the accuracy of automatic recognition of user voice commands, thereby enhancing overall user experience of using CIS, chat agents and similar digital personal assistant systems.

The invention provides a recognition method of a named entity and relates to the technical field of language recognition. The recognition method of the named entity adopts the mode of composite recognition, conducts word segmentation processing on each sentence firstly, (obtains the word units to be recognized) on the basis of the result of the word segmentation, confirms the word class, the language structure and the occurrence situation of the word unit to be recognized in various reference named dictionaries, and accurately confirm the recognition results of the name entity according to the occurrence situation (which reference named dictionary the word units to be recognized occurs in) of different word units in the reference named dictionaries and the word class and the language structure. Since each word unit to be recognized is matched with a corresponding reference named dictionary, more accurate recognition of the named entity can be conducted on the word units to be recognized according to the reference named dictionaries.