139 results about "Text stream" patented technology

Speech recognition is performed in near-real-time and improved by exploiting events and event sequences, employing machine learning techniques including boosted classifiers, ensembles, detectors and cascades and using perceptual clusters. Speech recognition is also improved using tandem processing. An automatic punctuator injects punctuation into recognized text streams.

A method of utilizing metadata stored in a computer-readable medium to assist in the conversion of an audio stream to a text stream. The method compares personally identifiable data, such as a user's electronic address book and/or Caller/Recipient ID information (in the case of processing voice mail to text), to the n-best results generated by a speech recognition engine for each word that is output by the engine. A goal of this comparison is to correct a possible misrecognition of a spoken proper noun such as a name or company with its proper textual form or a spoken phone number to correctly formatted phone number with Arabic numerals to improve the overall accuracy of the output of the voice recognition system.

A method for analyzing and indexing an unstructured or semistructured document according to one embodiment includes receiving an unstructured or semistructured document; converting the document to one or more text streams; analyzing the one or more text streams for identifying textual contents of the document; analyzing the one or more text streams for identifying logical sections of the document; associating the textual contents with the logical sections; indexing the textual contents and their association with the logical sections; and saving a result of the indexing in a data storage device.

The invention discloses a system and a method for filtering sensitive webpage, which is based on multi-classifier fusion. The processing object is a webpage, and the processing result is whether the webpage contains sensitive content, which may be pornography, reaction, violence and other unhealthy Internet contents harmful to society. The system comprises a data stream obtaining and preprocessing unit, an image and text stream filtering unit and an information fusion unit of image filter and text filter, by the cooperation of multiple classifiers, the system acquires source code of a webpage by using the URL of the webpage, a text and an image are separated at preprocessing stage to obtain text information and effective image information; an input webpage is divided into three modes by decision tree algorithm; the webpage is recognized by using a consecutive text classifier, a discrete sensitive text classifier and an image classifier, the output result recognized by the classifiers is fused and calculated, then a judge factor is given, and the final result is returned to a browser.

A relay is described to facilitate communication through the telephone system between hearing users and users who need or desire assistance in understanding voice communications. To overcome the speed limitations inherent in typing, the call assistant at the relay does not type most words but, instead, re-voices the words spoken by the hearing user into a computer operating a voice recognition software package trained to the voice of that call assistant. The text stream created by the computer and the voice of the hearing user are both sent to the assisted user so that the assisted user can be supplied with a visual text stream to supplement the voice communications. A time delay in the transmission of the voice of the hearing user through the relay is of assistance in the assisted user comprehending the communications session.

A computer-implemented method capable of identifying, activating, and executing commands, methods, functions, interfaces, and software-based applications that can satisfy a specific natural language user request represented by a text stream and generated from any means such as typing, voice, gestures, signs or by human thoughts.

A computer-implemented method for providing an objective evaluation to a customer service representative regarding his performance during an interaction with a customer may include receiving a digitized data stream corresponding to a spoken conversation between a customer and a representative; converting the data stream to a text stream; generating a representative transcript that includes the words from the text stream that are spoken by the representative; comparing the representative transcript with a plurality of positive words and a plurality of negative words; and generating a score that varies according to the occurrence of each word spoken by the representative that matches one of the positive words, and/or the occurrence of each word spoken by the representative that matches one of the negative words. Tone of voice, as well as response time, during the interaction may also be monitored and analyzed to adjust the score, or generate a separate score.

The invention provides an emergent topic detecting method and system facing text streams of a micro-blog platform. The method comprises the following steps that (1) user data and user generation information data of the micro-blog platform are collected in real time, and information text and images are extracted; (2) a time window is set, the information text is divided, and real-time data streams and historical data are obtained; (3) characteristics are selected, and training of a popularity evaluation model and a long micro-blog extraction model is carried out; (4) popularity evaluation is carried out on the real-time data streams by means of the popularity evaluation model, long micro-blog extraction is carried out on the real-time data streams by means of the long micro-blog extraction model, the information which is evaluated to be popular is put into popular information sets, and extracted long micro-blog contents are put into long micro-blog sets; (5) whether the number of the popular information sets and the number of the long micro-blog sets achieve preset threshold values is judged, if yes, topic extraction is carried out through an LDA model or in a weighting summation mode, emergent topics are extracted from data of the popular information sets and the long micro-blog sets, if no, the method goes back to the step (1).

A method and system for operational improvements in a dispatch console in a multi-source environment includes receiving (310) a plurality of audio streams simultaneously from a plurality of mobile devices, transcribing received audio streams by the means of speech-to-text conversion, presenting real-time transcriptions to the user and determining (320) if a first keyword is present in at least one of the plurality of audio and/or text streams. Upon determining the presence of the first keyword, the dispatch console automatically performs (330) at least one predefined dispatch console operation from a list of predefined dispatch console operations. The dispatch console further receives (340) a second keyword based on determining the presence of the first keyword and checks (350) for the presence of the second keyword within the audio and/or text streams thereby enabling additional automated dispatch console operations.

Disclosed are systems, apparatuses, circuits and methods for extrapolating meaning from vocalized speech or otherwise obtained text. Speech of a speaking user is sampled and digitized, the digitized speech is converted into a text stream, the text stream derived from speech or otherwise obtained is analyzed syntactically and semantically, a knowledgebase in the specific context domain of the text stream is utilized to construct one or more semantic/syntactic domain specific query analysis constrains/rule-sets, and a “Domain Specific Knowledgebase Query” (DSKQ) or set of queries is built at least partially based on the domain specific query analysis constrains/rule-sets.

A system and method that integrates automated voice recognition technology and speech-to-text technology with automated translation and closed captioning technology to provide translations of “live” or “real-time” television content is disclosed. It converts speech to text, translates the converted text to other languages, and provides captions through a single device that may be installed at the broadcast facility. The device accepts broadcast quality audio, recognizes the speaker's voice, converts the audio to text, translates the text, processes the text for multiple caption outputs, and then sends multiple text streams out to caption encoders and/or other devices in the proper format. Because it automates the process, it dramatically reduces the cost and time traditionally required to package television programs for broadcast into foreign or multi-language U.S. markets.

A system and method for analyzing text stream message for a micro-blog are provided. The system includes a sliding window module, storing a plurality of text stream messages from the micro-blog and updating the plurality of text stream messages once every preset duration; a dynamic text weight module, receiving the plurality of text stream messages and calculating the plurality of text stream messages for generating a burst weight according to a dynamic text stream weight algorithm; a clustering module, clustering the plurality of text stream messages for generating a plurality of clusters by a clustering algorithm according to the plurality of text stream messages and the burst weight; and a memory device, storing the clusters.

The invention relates to a method for detecting a burst topic in a user generation text stream based on graph clustering and belongs to the technical field of internet data mining. By the method, a graph-based new field of view relative to the conventional topic detection problem is provided, and the detection problem of the burst topic in the text stream is converted into a typical graph clustering problem, so the problem can be solved by using the conventional graph theory method. The method comprises the following main steps of: acquiring the text stream; detecting the burse topic; constructing a burst word graph; and clustering burst words. The method aims at the detection of the burst topic in the user generation text stream and has the performance which is superior to that of the conventional method based on document clustering, a probability topic model and burst characteristic clustering.

The invention discloses a searching method and searching device based on text. The searching method based on text includes: step 1, acquiring feature words included in text streams which are sent by users, step 2, acquiring a feature probability of every business, which corresponds to every feature word from a pre-built feature probability lexicon, step 3, calculating a joint probability of every business, which corresponds to the text streams, according to the feature probability of every business, which corresponds to every feature word and step 4, outputting final matching business according to the joint probability acquired by calculating, storing every feature word in the feature probability lexicon and updating the corresponding feature probability of the feature word in the feature probability lexicon. According to the searching method and searching device based on text, the searching efficiency can be increased and operating costs can be reduced.

The invention discloses a method and a device for mining hot-spot words. The method includes acquiring input text streams; subjecting the text streams to word segmentation to obtain a candidate word set; accounting a current frequency that each candidate word in the candidate word set appears in the text streams to acquire each history frequency of each candidate word in prestored history data; and calculating a frequency abnormity value of the candidate word according to the current frequency and each history frequency of the candidate word, storing a current frequency message of the candidate word in the history data, and outputting a preset number of candidate words with abnormal frequencies. By means of the method and the device for mining the hot-spot words, mining ranges of the hot-spot words can be extended, and mining efficiencies of the hot-spot words can be improved.

A method, apparatus and computer program product are provided for synchronizing separate compressed video and text streams to provide lightweight closed captioning and instant messaging integration with video conferencing. A video encoder encodes a video stream and periodically generates a synchronization frame event. Each generated synchronization frame event has a unique ID. A text recording agent receives the periodically generated synchronization frame events, and generates text packets associating stored text with the synchronization frame event. A video decoder decodes the video stream, periodically generating the synchronization frame event having the unique ID. A text display agent receives the periodically generated synchronization frame events and associates stored text packets with the synchronization frame events.

A system for translating speech from at least two source languages into another target language provides direct speech to target language translation. The target text is converted to speech in the target language through a TTS system. The system simplifies speech recognition and translation process by providing direct translation, includes mechanisms described herein that facilitate mixed language source speech translation, and punctuating output text streams in the target language. It also in some embodiments allows translation of speech into the target language to reflect the voice of the speaker of the source speech based on characteristics of the source language speech and speaker's voice and to produce subtitled data in the target language corresponding to the source speech. The system uses models having been trained using (i) encoder-decoder architectures with attention mechanisms and training data using TTS and (ii) parallel text training data in more than two different languages.

The invention is suitable for the technical field of application of electronic books and provides a method and system for displaying a PDF (Portable Document Format) document adaptively to a window size, and a mobile terminal. The method comprises the following steps of: A, extracting a locally-stored PDF document and selecting the range of pages to be resolved from the locally-stored PDF document; B, resolving information in the selected page range according to a preset resolving object type to obtain attribute information of each resolving object, wherein the attribute information of each resolving object comprises the position information of each resolving object; C, typesetting each resolving object according to corresponding position information of each resolving object; and D, writing the typeset resolving objects into a document which can support word wrap in a text stream write-in mode, and displaying information in the document. By adopting a PDF document displaying technology provided by the invention, a PDF page can be read without adjusting a display window leftwards or rightwards, and better reading experience and great convenience can be brought to a user.

There is provided a system for the automatic collection and conditioning of closed caption texts originating from multiple geographic locations, comprising: (1) at least one remote capture client means having a tuner to receive one or more television signals, a decoder to decode closed caption text stream in the television signals, and means to write the closed caption text stream to a text file, (2) central server means operatively connected to the remote capture client means for storing the text files and making the text files available to a user, and (3) an inquiry client means operatively connected to the central server means for searching the text files. The central server is adapted to automatically process search requests from the inquiry client and notify the inquiry client via any suitable communications means, even when the inquiry client is not in active communication with the central server.