183 results about "Language identification" patented technology

An apparatus for providing flexible text based language identification includes an alphabet scoring element, an n-gram frequency element and a processing element. The alphabet scoring element may be configured to receive an entry in a computer readable text format and to calculate an alphabet score of the entry for each of a plurality of languages. The n-gram frequency element may be configured to calculate an n-gram frequency score of the entry for each of the plurality of languages. The processing element may be in communication with the n-gram frequency element and the alphabet scoring element. The processing element may also be configured to determine a language associated with the entry based on a combination of the alphabet score and the n-gram frequency score.

A voice-controlled data system may include a data storage unit including media files having associated file identification data, and a vocabulary generating unit generating phonetic data corresponding to the file identification data, the phonetic data being supplied to a speech recognition unit as a recognition vocabulary, where one of the media files may be selected according to a recognized speech control command on the basis of the generated phonetic data, where the file identification data include a language identification part for identifying the language of the file identification data, and where the vocabulary generating unit generates the phonetic data for the file identification data of a media file based on its language identification part.

Systems and processes for language identification from short strings are provided. In accordance with one example, a method includes, at a first electronic device with one or more processors and memory, receiving user input including an n-gram and determining a similarity between a representation of the n-gram and a representation of a first language. The representation of the first language is based on an occurrence of each of a plurality of n-grams in the first language and an occurrence of each of the plurality of n-grams in a second language. The method further includes determining whether the similarity between the representation of the n-gram and the representation of the first language satisfies a threshold.

A language recognition system, method and program product for recognizing language based input from computer users on a network of connected computers. Each computer includes at least one user based language model trained for a corresponding user for automatic speech recognition, handwriting recognition, machine translation, gesture recognition or other similar actions that require interpretation of user activities. Network computer users are clustered into classes of similar users according to user similarities such as, nationality, profession, sex, age, etc. User characteristics are collected by sensors and from databases and, then, distributed over the network during user activities. Language models with similarities among similar users on the network are identified. The language models include a language model domain, with similar language models being clustered according to their domains. Language models identified as similar are modified in response to user production activities. After modification of one language model, other identified similar language models are compared and adapted. Also, user data, including information about user activities and language model data, is transmitted over the network to other similar users. Language models are adapted only in response to similar user activities, when these activities are recorded and transmitted over the network. Language models are given a global context based on similar users that are connected together over the network.

The present invention learns phrase translation relationships by receiving a parallel aligned corpus with phrases to be learned identified in a source language. Candidate phrases in a target language are generated and an inside score is calculated based on word association scores for words inside the source language phrase and candidate phrase. An outside score is calculated based on word association scores for words outside the source language phrase and candidate phrase. The inside and outside scores are combined to obtain a joint score.

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.

Systems and processes for language identification using recurrent neural networks are provided. An example method includes, at an electronic device, receiving a first typed character of a character sequence and determining a character context of the first typed character based on the first typed character and a second typed character of the character sequence. The method further includes determining a confidence level that the character sequence is associated with a language of a plurality of languages based on the character context of the first typed character, and determining whether the confidence level exceeds a threshold, in accordance with a determination that the confidence level exceeds the threshold, providing the language as a candidate language, and in accordance with a determination that the confidence level does not exceed the threshold, forgoing providing the language as a candidate language.

A system and methods of language identification of natural language text are presented. The system includes stored expected character counts and variances for a list of characters found in a natural language. Expected character counts and variances are stored for multiple languages to be considered during language identification. At run-time, one or more languages are identified for a text sample based on comparing actual and expected character counts. The present methods can be combined with upstream analyzing of Unicode ranges for characters in the text sample to limit the number of languages considered. Further, n-gram methods can be used in downstream processing to select the most probable language from among the languages identified by the present system and methods.

Systems and processes for language identification from short strings are provided. In accordance with one example, a method includes, at a first electronic device with one or more processors and memory, receiving user input including an n-gram and determining a similarity between a representation of the n-gram and a representation of a first language. The representation of the first language is based on an occurrence of each of a plurality of n-grams in the first language and an occurrence of each of the plurality of n-grams in a second language. The method further includes determining whether the similarity between the representation of the n-gram and the representation of the first language satisfies a threshold.

In some preferred embodiments, a language identification apparatus, comprises a storing means 32 configured to store undefined character code lists of a plurality of languages to which no character is allotted in a character code table of each language, a collating means 34 configured to collate a character code of each character contained in a character string of a language identification target with the undefined character code list of each language stored in the storing means, and an identification means 34 configured to identify a language in which a character corresponding to the undefined character code is not contained in the character string as a language of the character string among the plurality of languages as a result of collation by the collating means.

The invention discloses an intelligent household control system based on a multichannel interaction manner. The intelligent household control system comprises a controller and a control network, wherein the controller comprises a front-end sensor, a signal preprocessing module and a core processing chip, wherein the front-end sensor comprises a front-end camera and an audio sensor; the signal preprocessing module comprises a video preprocessing module and an audio preprocessing module; the core processing chip comprises a lip language identification module, a human face identification module and a hand gesture identification module and a voice identification module; and the control network comprises a controller communication module arranged on the controller and a household appliance communication module arranged on a household appliance. The intelligent household control system disclosed by the invention makes use of advantages of various technologies in respective application field, learns from each other, makes various technical modules relatively independent and mutually fused and realizes stability and operation comfortability.

A speech recognition system comprising: a language identification unit for identifying the language of a text item entry; at least one separate pronunciation modelling unit including a phoneme set and pronunciation model for at least one language; means for activating the pronunciation modelling unit including the phoneme set and pronunciation model for the language corresponding to the language identified in the language identification unit for obtaining a phoneme transcription for the entry; and a multilingual acoustic modelling unit for creating a recognition model for the entry.

A method for training a multi-language speech recognition network includes providing utterance datasets corresponding to predetermined languages, inserting language identification (ID) labels into the utterance datasets, wherein each of the utterance datasets is labelled by each of the language ID labels, concatenating the labeled utterance datasets, generating initial network parameters from the utterance datasets, selecting the initial network parameters according to a predetermined sequence, and training, iteratively, an end-to-end network with a series of the selected initial network parameters and the concatenated labeled utterance datasets until a training result reaches a threshold.

A method and apparatus for a credit card and debit card transaction terminal including a processor, a display and a memory. A card reader is configured to read data stored on a portable memory medium. An operator interface is produced by an operator interface program and executable by the processor. The operator interface being displayable on the display in an operator language. A customer interface is produced by a customer interface program and executable by the processor. The customer interface being displayable in a customer language. A language identification module is stored in the memory and executable on the processor. The language identification module is configured to select the operator language and to select a customer language in which displayable for the operator and customer, respectively. The operator and customer languages are selected from a plurality of languages stored in the module. The operator and customer languages are different.

The present invention provides a head carried stereo vision hand gesture identifying device and belongs to the field of computer vision and man-computer interaction technology. The head carried stereo vision hand gesture identifying device consists of four parts: stereo vision imaging head, stereo vision board, head carried display and worn computer. The stereo vision imaging head obtains the hand grey image of the wearer; the stereo vision board calculates the real-time the dense parallax map and transmits the dense parallax map and the grey image to the worn computer; and the worn computer completes hand tracking and hand gesture identifying operation and showing the calculation results in the head carried display. The present invention can realize the hand tracking and hand gesture identifying under worn computer environment, complete hand gesture mouse, hand language identification, hand written character identification, etc. and intelligent man-computer interface based on hand gesture.

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.

Multiple nonoverlapping languages within a single document can be identified. In one embodiment, for each of a set of candidate languages, a set of non-overlapping languages is defined. The document is analyzed under the hypothesis that the whole document is in one language and that part of the document is in one language while the rest is in a different, non-overlapping language. Language(s) of the document are identified based on comparing these competing hypotheses across a number of language pairs. In another embodiment, transitions between non-overlapping character sets are used to segment a document, and each segment is scored separately for a subset of candidate languages. Language(s) of the document are identified based on the segment scores.

A system and method for text language identification allow private information of a server and a client to be kept secret from each other. An encrypted score for each of a plurality of languages is received by the server from the client. The encrypted scores are generated by homomorphic addition of encrypted frequencies of n-grams in a list of n-grams extracted from text. The unencrypted list is not provided to the server. The encrypted frequencies of the n-grams in the list are extracted using encrypted resources which, for each of the plurality of languages, include an encrypted frequency for each of a set of n-grams. At the server, the encrypted scores are decrypted to generate unencrypted scores and information is provided to the client based on the unencrypted scores from which the client is able to identify a language for the text.

The present invention is a method and apparatus for processing a phrase in a first language for translation to a second language. A plurality of possible linguistic patterns are identified in the second language, that correspond to the phrase in the first language. For each of the patterns identified, a probability for the pattern is calculated, based on a combination of the language model probability for the pattern and a translation model probability for the pattern. In one embodiment, an output is also provided which is indicative of a translation of the phrase in the first language to the second language based upon the translation probabilities calculated for the patterns.

An apparatus for providing flexible text based language identification includes an alphabet scoring element, an n-gram frequency element and a processing element. The alphabet scoring element may be configured to receive an entry in a computer readable text format and to calculate an alphabet score of the entry for each of a plurality of languages. The n-gram frequency element may be configured to calculate an n-gram frequency score of the entry for each of the plurality of languages. The processing element may be in communication with the n-gram frequency element and the alphabet scoring element. The processing element may also be configured to determine a language associated with the entry based on a combination of the alphabet score and the n-gram frequency score.

The invention belongs to the field of computers, in particular to a human-computer interaction identification system applied to remote information services, characterized in that the service system providing network information services or its client has at least one human-computer interaction identification device; The computer-interactive recognition device includes: an auditory collection module for collecting user voice signals; a visual collection module for collecting user face images; a first preprocessing module, a face feature extraction module, and a face recognition module; a second Preprocessing module, speech feature extraction module, speech recognition module; third preprocessing module, facial expression feature extraction module, facial expression recognition module; fourth preprocessing module, language emotion feature extraction module, language emotion recognition module; The gender recognition fusion module is used to fuse the recognition results of the face recognition module and the voice recognition module to form a recognition result that combines face features and voice features; the implicit recognition fusion module is used to integrate the facial expression recognition module It is fused with the recognition results of the language emotion recognition module to form a recognition result that combines facial expression features and voice emotion features.

The invention discloses a dual-language coordinated training-based named entity identification method, and belongs to the technical field of natural language processing in computer science. Parallel Chinese and English sentence datasets are considered as two different view of a dataset for dual-language coordinated training, a log-linear model is used for correcting projection marks in a projection process, and named entity dual-language aligned annotation consistency is introduced as a measurement index for mark confidence estimation when the model is used for predicting an unseen case. Compared with the prior art, the method has the advantages that the domain dependence of named entity identification is reduced, the advantages of dual-language identification are fused, the problem of partial identification ambiguity in single-language identification is solved, and the method is particularly suitable for the dual-language named entity synchronous identification of large-scale language materials.

The embodiment of the invention provides a modeling method for language identification, which comprises the following steps of: inputting voice data, preprocessing the voice data to obtain a characteristic sequence, mapping a characteristic vector to form a super vector, performing projection compensation on the super vector, and establishing a training language model through an algorithm of a support vector machine; and adopting the steps to obtain a super vector to be measured of the voice to be measured, performing the projection compensation on the super vector to be measured, grading the super vector to be measured by utilizing the language model, and identifying language types of the voice to be measured. The embodiment of the invention also provides a modeling device for the language identification, which comprises a voice preprocessing module, a characteristic extraction module, a multi-coordinate system origin selection module, a characteristic vector mapping module, a subspace extraction module, a subspace projection compensation module, a training module and an identification module. According to the method and the device which are provided by the embodiment of the invention, information which is invalid to the identification in high-dimension statistics is removed, the correction rate of the language identification is improved, and the computational complexity on an integrated circuit is reduced.

A method, apparatus, and computer instructions for processing calls. Initiation of a call by a user is detected in the communications device. In response to detecting the call, a geographic identification based on a number assigned to the communications device and / or a language identification based on a user of the communications device is identified. The geographic identification and the language identification are transmitted with caller identification information for use by a called party.

The invention discloses a language identification method of a scene text image in combination with global and local information. Basic features of a character image are extracted, and then global andlocal feature representations are extracted respectively; the global extraction branch uses global maximum pooling to express the whole graph as a vector, and category score prediction is carried out;probability prediction is performed on the local blocks of the image by the local aggregation branches respectively, and then the series of probability distributions are combined to obtain a categoryprediction score of a local level; and finally, global and local prediction scores are dynamically fused according to the branch prediction conditions to obtain a final identification result. According to the method, overall features and local differentiated features of the character images are noticed at the same time, and end-to-end training can be achieved in one step. Compared with an existing technology utilizing local features, the method has the advantages that the local differentiated features can be accurately extracted, excellent effects are achieved in the aspects of accuracy, operation efficiency and universality, and high practical application value is achieved.

A WEB page translation method includes a description language identification means 33 for discriminating whether the translation target portion of the WEB page accessed by a user via a terminal device 1 is described in HTML, a first translation means 35 for translating the character string displayed on the WEB page into another language on a translation target portion discriminated to be described in HTML by the description language identification means 33, and a second translation means 36 for translating the character string displayed on the WEB page into another language on a translation target portion discriminated to be described not in HTML by the description language identification means 33.

The invention discloses a system language setting method and device, and belongs to the field of language processing. The system language setting method comprises steps of acquiring voice information; carrying out language identification to the voice information, and determining the language kind corresponding to the voice information; and switching the system language of an intelligent device to a language corresponding to the obtained language kind. According to the invention, a microphone of the intelligent device is employed to acquire and identify the voice information to determine the language kind corresponding to the voice information;, and the system language of the intelligent device is switched to the language corresponding to the obtained language kind, the intelligent device can directly switch the system language in dependence on the voice information obtained by the microphone, and therefore the problem that the manner of obtaining the language by means of SIM card information is not accurate is solved, and the effect that the intelligent device switches the system language in dependence on the user's actual language usage case, and the switching accuracy of the system language of the intelligent device is improved is achieved.

An intelligent cross-language speech recognition and conversion method claimed by the present invention classifies speech data based on the language family, establishes inter-language distances, initially determines a language family to which to-be-recognized speech data belongs, and then performs language refined identification in the language family. After the first language identification error, neighbor language families can be further found based on established inter-language distances, and the language family is established; and after the language is identified, the language is convertedinto a standardized text, then the text is subjected to word segmentation, word frequency statistics and other processing to establish the mapping relationship, which facilitates subsequent voice query. On the one hand, the method effectively solves the disadvantages that the efficiency and the speed cannot be balanced in the current speech recognition. On the other hand, the processing of the speech text conversion is more reasonable, and the establishment of mapping relationship makes the recognition conversion efficiency more accurate.

The invention provides a balance method of actual scene linguistic data and finite state network (FSN) linguistic data. In order to train the language model of a continuous speech recognizer, training linguistic data is produced according to the application field of the speech recognizer. Linguistic data mainly has two resources: one part is an actual scene linguistic data which is obtained by tidying records in actual scene, and the other part is FSN linguistic data generated with a finite state network syntactic rule method. Two linguistic data balance methods are mainly researched in the invention, and the invention provides a method that probability comparison of the keyword shared by the actual scene linguistic data and the FSN linguistic data is taken as basis, and a certain multiple of parts of actual scene linguistic data are used for expanding the FSN linguistic data to obtain the final method of language model training linguistic data. The language model for training linguistic data, which is obtained with the method, greatly improves the recognition performance of the continuous speech recognizer.