566 results about "Word recognition" patented technology

The invention relates to a system and method for processing natural language text utilizing disambiguation components to identify a disambiguated sense for the text. For the method, it comprises applying a selection of the components to the text to identify a local disambiguated sense for the text. Each component provides a local disambiguated sense of the text with a confidence score and a probability score. The disambiguated sense is determined utilizing a selection of local disambiguated senses. The invention also relates to a system and method for generating sense-tagged text. For the method, it comprises steps of: disambiguating a quantity of documents utilizing a disambiguation component; generating a confidence score and a probability score for a sense identified for a word provided by the component; if the confidence score for the sense for the word is below a set threshold, the sense is ignored; and if the confidence score for the sense for the word is above the set threshold, the sense is added to the sense-tagged text.

Disclosed is a remote control device that interacts with a set-top box to provide selective programming and / or enhanced content based upon the identity of the user of the remote control. The present invention utilizes preference and profile data corresponding to the current user to control the video output and / or enhanced content of the display. The present invention can also select or exclude video or enhanced content based upon tags that describe video content and the identity of the user based upon the use of a personalized remote control. The present invention can employ recognition techniques, such as word recognition, image recognition and sound recognition to restrict or select video content based upon the identity of the user of a personalized remote control device.

One aspect of the invention involves word recognition that uses scrollable choice lists in which choices are listed in character-order. Another aspect relates to a scrollable, visually-displayed word recognition choice list, where the recognition candidates on the choice list are each associated with a choice-selecting symbol the user can use to select a desired recognition candidate by pressing an associated button, and where the same choice-selecting symbol is used for different choices displayed on the display at different times as a result of scrolling. Another aspect of the invention relates to providing a choice list of best scoring characters for a particular character position in the spelling of a filter that is used to filter word recognition. Another aspect of the invention relates to a choice list used in word recognition in which the choice list can be scrolled horizontally.

Methods and apparatus are provided for automatically detecting spelling errors in one or more documents, such as documents being processed for the creation of a lexicon According to one aspect of the invention, a spelling error is detected in one or more documents by determining if at least one given word in the one or more documents satisfies a predefined misspelling criteria, wherein the predefined misspelling criteria comprises the at least one given word having a frequency below a predefined low threshold and the at least one given word being within a predefined edit distance of one or mote other words in the one or more documents having a frequency above a predefined high threshold; and identifying a given word as a potentially misspelled word if the given word satisfies the predefined misspelling criteria

A computer program for execution on a computing device is provided to cross-train students in language development skills such as letter-word correspondence, word recognition, vocabulary, and sentence and paragraph comprehension. A set of programs provide an adaptive methodology for training a student in decoding (semantic, syntactic, phonological, and morphological relationships), knowledge of rhymes, synonyms, antonyms, and homophones, spelling, letter-word correspondences, sentence comprehension, grammatical comprehension, working memory, vocabulary, paragraph comprehension, and improved reading comprehension. In each program, students are presented with an animated scene that poses a question, and a set of answers. The set of answers contain a correct response, and a number of incorrect responses or foils. The student advances to more complex levels by satisfying predetermined correct thresholds. Through repetition and intensity, the student's language skills are developed.

The invention relates to a method for selecting language for word recognition in a data processing device, wherein at least two different languages are selectable for word recognition. The data processing device stores at least one predetermined rule specifying how language for word recognition is to be selected for a word recognition event. The method includes the step of selecting the language according to the predetermined rule prior to the word recognition.

A method of recognizing a handwritten word of cursive script comprising providing a template of previously classified words, and optically reading a handwritten word so as to form an image representation thereof comprising a bit map of pixels. The external pixel contour of the bit map is extracted and the vertical peak and minima pixel extrema on upper and lower zones respectively of this external contour are detected. Feature vectors of the vertical peak and minima pixel extrema are determined and compared to the template so as to generate a match between the handwritten word and a previously classified word. A method for classifying an image representation of a handwritten word of cursive script is also provided. Also provided is an apparatus for recognizing a handwritten word of cursive script. This apparatus comprises a template of previously classified words, a reader for optically reading a handwritten word, and a controller being linked thereto for generating a match between the handwritten word and the previously classified words. Two algorithms are provided for respectively correcting the skew and slant of a word image.

In order to handle portions of a recognized sentence having an error, a speaker or user is questioned about contents associated with the portions, and according to a user's answer a result is obtained. A speech recognition unit extracts a speech feature of a speech signal inputted from a user and finds a phoneme nearest to the speech feature to recognize a word. A recognition error determination unit finds a sentence confidence based on a confidence of the recognized word, performs examination of a semantic structure of a recognized sentence, and determines whether or not an error exists in the recognized sentence which is subject to speech recognition according to a predetermined criterion based on both the sentence confidence and a result of examining the semantic structure of the recognized sentence. Further, a meta-dialogue generation unit generates a question asking the user for additional information based on a content of a portion where the error exists and a type of the error.

A method and apparatus is disclosed for remotely processing voice commands for controlling a television. A voice command is uttered by a user into a microphone contained in a remote control. The voice command is digitized, modulated, compressed, and wirelessly transmitted to a wireless receiver connected to a set-top box. The voice command is then transmitted to a cable head-end unit for voice and word recognition processing. Once the command function is determined, the function is transmitted back to the set-top box where the set-top box performs the command. The microphone is activated and deactivated by pressing and releasing a push-to-talk (PTT) switch. The PTT activates other functions by being turned, double-clicked and toggled up and down, left and right.

One-to-many comparisons of callers' words and / or voice prints with known words and / or voice prints to identify any substantial matches between them. When a customer communicates with a particular entity, such as a customer service center, the system makes a recording of the real-time call including both the customer's and agent's voices. The system segments the recording to extract different words, such as words of anger. The system may also segment at least a portion of the customer's voice to create a tone profile, and it formats the segmented words and tone profiles for network transmission to a server. The server compares the customer's words and / or tone profiles with multiple known words and / or tone profiles stored on a database to determine any substantial matches. The identification of any matches may be used for a variety of purposes, such as providing representative feedback or customer follow-up.

Disclosed embodiments of the invention provide automated global optimization methods and systems of OCR, tailored to each document being digitized. A document-specific database is created from an OCR scan of a document of interest, which contains an exhaustive listing of words in the document. Images of each word, taken from all the fonts encountered, are entered into the database and mapped to a corresponding textual representation. After entry of a first instance of an image of a word written in a particular font, each new occurrence of the word in that font can be quickly recognized by image processing techniques. The disclosed methods and systems may be used in conjunction with adaptive character recognition training and word recognition training of the OCR engines.

One-to-many comparisons of callers' words and / or voice prints with known words and / or voice prints to identify any substantial matches between them. When a customer communicates with a particular entity, such as a customer service center, the system makes a recording of the real-time call including both the customer's and agent's voices. The system segments the recording to extract different words, such as words of anger. The system may also segment at least a portion of the customer's voice to create a tone profile, and it formats the segmented words and tone profiles for network transmission to a server. The server compares the customer's words and / or tone profiles with multiple known words and / or tone profiles stored on a database to determine any substantial matches. The identification of any matches may be used for a variety of purposes, such as providing representative feedback or customer follow-up.

The invention discloses a microblog user interest recognizing method based on text mining, and belongs to the field of text mining and natural language processing. The method includes the steps of collecting the newest topical microblog text data of a microblog text set and microblog text data of a designated user, standardizing the collected microblog text data, recognizing the newest microblog words and renewing a new word dictionary for the standardized topical microblog text data through the microblog new word recognition method, conducting Chinese character word separation on the standardized microblog text data of the designated user through the new word dictionary word separation method to achieve text vector expression, clustering the microblog text data, expressed through text vectors, of the designated user, recombining original microblog text data, extracting new text set features through a topic model, presetting topic dictionaries, calculating the weight of each topic dictionary based on the new text set features to obtain the final topic, and enabling the final topic to serve as the microblog user interest recognition, thereby improving accuracy of feature extraction.

Speech recognition models are dynamically re-configurable based on user information, application information, background information such as background noise and transducer information such as transducer response characteristics to provide users with alternate input modes to keyboard text entry. Word recognition lattices are generated for each data field of an application and dynamically concatenated into a single word recognition lattice. A language model is applied to the concatenated word recognition lattice to determine the relationships between the word recognition lattices and repeated until the generated word recognition lattices are acceptable or differ from a predetermined value only by a threshold amount. These techniques of dynamic re-configurable speech recognition provide for deployment of speech recognition on small devices such as mobile phones and personal digital assistants as well environments such as office, home or vehicle while maintaining the accuracy of the speech recognition.

Alphabetic filtering of the speech recognition of words uses a key press to indicate a desired character in an alphabetic filter string, where each key press represents two or more letters. The key presses can be disambiguated by recognizing a key-disambiguation utterance in association with a given key press. A user can select a desired recognition candidate from a choice list produced by such filtered word recognition. Ambiguous alphabetic filtering can be performed iteratively in response to the addition of successive ambiguous key presses. A user can select to re-recognize the utterance using filtering based on ambiguous key input after seeing the results of recognition without such filtering. Unambiguous alphabetic filtering can be performed by using multiple presses of an ambiguous key to disambiguate which letter is intended. A user can select between entering text by either large vocabulary speech recognition or by spelling text by pressing phone keys.

The invention discloses a method for detecting and recognizing sensitive characters in natural scene images, which comprises the following steps of obtaining a training sample, wherein the training sample data comprises a self-built natural scene sensitive text data set and a public text data set; the training sample data comprises a self-built natural scene sensitive text data set and a public text data set; establishing and training the model of direct recognition of sensitive characters based on improved DSSD network; obtaining a test sample image in a natural scene, inputting that test sample image into the sensitive character direct recognition model, detecting and recognizing the sensitive character in the test image, and realizing the sensitive word recognition of a multi-directional and complex changing text region under the natural scene. The method of the invention solves the problem of the stability of the character recognition based on the single character, solves the character sample problem, simplifies the recognition process, and greatly improves the detection and recognition speed and the precision of the sensitive character in the natural scene, and can recognize the sensitive words in multi-directional and complex text regions in natural scenes.

A method for teaching a child to read based on the training of a set of words or phrases whereby the past comprehension history of that child for each of the words and phrases is used to formulate a specific presentation, teaching and assessment strategy which will vary from word to word and phase to phrase, with the objective of teaching the child to read and recognize new words and phrases while at the same time consolidating the recognition of better understood words and phrases in order to reduce the onset of poor reading habits such as word vocalization, eye overuse and eye skip back (regression). The interactive reading tutor application may be access locally or remotely accessed by users via a network such as the Internet. This invention can also be used to train adults with poor reading skills, readers with reading disorder, and persons learning a second or subsequent language. The invention may be used to teach languages other than English.

This invention discloses a voice enabled knowledge system, comprising a speech recognition engine and text to speech engine. The speech recognition engine further comprises a representation unit to represent the spoken words, a model classification unit to classify the spoken words, a training database to match the spoken words with preset words and a search unit to search for the spoken word in said training database, based on the results of said model classification. The text to speech engine for conversion of an input text to speech, comprises a text pre-processing unit for analyzing the input text in a sentence form, a prosody unit for word recognition using said acoustic model, a concatenation unit for converting the diphone equivalents into words and thereafter into a sentence and an audio output device for speech output.

A computer-based detection (e.g., speech recognition) system combines a word decoder and subword decoder to detect words (or phrases) in a spoken input provided by a user into a speaker connected to the detection system. The word decoder detects words by comparing an input pattern (e.g., of hypothetical word matches) to reference patterns (e.g., words). The subword decoder compares an input pattern (e.g., hypothetical words matches based on subword or phoneme recognition) to reference patterns (e.g., words) based on a word pronunciation distance measure that indicates how close each input pattern is to matching each reference pattern. The subword decoder sorts the source set of reference patterns based on a closeness of each reference pattern to correctly matching the input pattern based on generated pattern comparisons. The word decoder and subword decoder each provide an N-best list of hypothetical matches to the spoken input. A list fusion module of the detection system selectively combines the two N-best lists to produce a final or combined N-best list. The final or combined list has a predefined number of matches.

The invention provides a continuous voice recognition method based on a deep long and short term memory recurrent neural network. According to the method, a noisy voice signal and an original pure voice signal are used as training samples, two deep long and short term memory recurrent neural network modules with the same structure are established, the difference between each deep long and short term memory layer of one module and the corresponding deep long and short term memory layer of the other module is obtained through cross entropy calculation, a cross entropy parameter is updated through a linear circulation projection layer, and a deep long and short term memory recurrent neural network acoustic model robust to environmental noise is finally obtained. By the adoption of the method, by establishing the deep long and short term memory recurrent neural network acoustic model, the voice recognition rate of the noisy voice signal is improved, the problem that because the scale of deep neutral network parameters is large, most of calculation work needs to be completed on a GPU is avoided, and the method has the advantages that the calculation complexity is low, and the convergence rate is high. The continuous voice recognition method based on the deep long and short term memory recurrent neural network can be widely applied to the multiple machine learning fields, such as speaker recognition, key word recognition and human-machine interaction, involving voice recognition.

A system for spacing, storing and recognizing electronic representations of handwriting and printing comprises a central processing unit that couples with a display device, an input device, and a memory. The memory includes means for spacing ink stroke representations, means for recognizing outline elements, means for performing deferred recognition, means for highlighting drawing areas and means for storing and displaying ink stroke representations. These means operate together to provide a pen-based or graphics oriented computer system with improved performance and added functionality for manipulating the space between ink stroke representations. The preferred embodiment of the present invention comprises several novel methods that provide this functionality including: a method for managing space between ink stroke representations, a method for displaying drawing elements in a visually distinct manner, a method for recognizing bullets and dashes, a method for storing ink stroke representations, a method for displaying and printing ink stroke representations, and a method for performing deferred character or word recognition.

The invention relates to an event trigger word extraction method, in particular to an event trigger word extraction method based on a document level attention mechanism, comprising the following steps: (1) preprocessing training corpus; (2) performing word vector training by using PubMed database corpus; (3) constructing a distributed representation way of a sample; (4) constructing a characteristic representation way based on BiLSTM-Attention; (5) adopting CRF learning, and acquiring an optimal sequence labeling result of the current document sequence; and (6) extracting event trigger words.The method provided by the invention has the advantages that firstly a BIO tag labeling way is adopted, and recognition including multi-word trigger word recognition is realized; secondly a corresponding simple word and characteristic distributed representation way is constructed for a trigger word recognition task; and thirdly, a BiLSTM-Attention model is proposed, a distributed representation structure specific to the currently input document level information is realized by introducing an Attention mechanism, and trigger word recognition effect is improved.

Alphabetic filtering of the speech recognition of words uses a key press to indicate a desired character in an alphabetic filter string, where each key press represents two or more letters. The key presses can be disambiguated by recognizing a key-disambiguation utterance in association with a given key press. A user can select a desired recognition candidate from a choice list produced by such filtered word recognition. Ambiguous alphabetic filtering can be performed iteratively in response to the addition of successive ambiguous key presses. A user can select to re-recognize the utterance using filtering based on ambiguous key input after seeing the results of recognition without such filtering. Unambiguous alphabetic filtering can be performed by using multiple presses of an ambiguous key to disambiguate which letter is intended. A user can select between entering text by either large vocabulary speech recognition or by spelling text by pressing phone keys.

The invention proposes a voice wakeup method and a voice wakeup device based on artificial intelligence. The voice wakeup method comprises the following steps: acquiring pronunciation information corresponding to a custom wakeup word; acquiring approximate pronunciation information corresponding to the pronunciation information; and building a wakeup word recognition network according to a preset spam word list, the pronunciation information and the approximate pronunciation information so as to recognize voice input by a user according to the wakeup word recognition network and determine whether or not need to perform a wakeup operation according to the recognition result. According to the embodiments of the invention, a wakeup word recognition network can be built dynamically for different custom wakeup, so that the accuracy of wakeup is enhanced effectively, the rate of false alarm is reduced, and the wakeup efficiency is improved. The device has smaller memory footprint and low power consumption.

A non-transitory processor readable medium storing processor executable instructions is described. The processor executable instructions, when executed by a processor, cause the processor to: receive application data indicative of text from a user device via a communications network; analyze the application data for one or more indicator being at least a portion of the text entered into the application and having one or more meaning; retrieve one or more selected ideograph from a database populated with ideographs received from and associated with one or more advertisers, the one or more selected ideograph being indicative of a graphical representation of the one or more meanings of the one or more indicator; transmit the one or more selected ideograph to the user device via the communications network; and charge a fee to at least one advertiser associated with the one or more selected ideograph.

A method and apparatus are provided for authenticating a user using verbal information verification techniques. The user is challenged with one or more questions that the user has previously answered. A user's spoken utterances are first processed using automatic speech recognition techniques, and optionally utterance verification techniques. The recognized text that has been extracted from the user's spoken words is compared with the information recorded in a user profile corresponding to the answers provided by the user during the enrollment phase, using word spotting techniques. If the user's spoken answer is correct, the user may obtain access to a protected resource. If the user's spoken answer provided during verification deviates from the answer that was provided during enrollment, the disclosed verbal input verification server can still correctly recognize the answer.