Abstract: A system for translating text from a source language to a target language comprising a user client program component running over a local PC of a user, from which a translation request is sent; a server program component running over a server workstation; and a translator client program running over a local PC of a translator, from which a translation request is processed.

Abstract: Paralinguistic indicators are translated at a paralinguistic translation server by receiving from a source a first set of data related to a first paralinguistic indicator that is configured to enable non-verbal communications between a source and a destination. The source is one of an instant messaging system and a virtual world system and the destination is one of the textual instant messaging system and a virtual world system but differs from the source. The first set of data related to the first paralinguistic indicator is translated into a second set of data related to a second paralinguistic indicator, such that the second paralinguistic indicator that is at least partially synonymous to the non-verbal communications associated with the first paralinguistic indicator. The second set of data related to the second paralinguistic indicator is transmitted to the destination.

Abstract: Methods, apparatus and systems, including computer program products, for reducing an error rate when mapping entities between a first ontology and a second ontology. One or more of a general language dictionary and an industry-specific dictionary are provided. Natural language processing of the first ontology is performed to identify one or more candidate relationship entities in the first ontology. Each candidate relationship entity includes a compound name having two or more semantic labels, and each candidate relationship entity has a name that neither exists in the general language dictionary or the industry-specific dictionary. Each of the one or more candidate relationship entities in the first ontology is mapped to one or more entities in the second ontology using one or more configurable computer-implemented mapping algorithms.

Abstract: A speech translator includes a device adapted to be worn in the ear and includes means responsive to audible speech in a first language to convert that speech to electrical signals representing words and phrases and applying the signals to a database to retrieve other signals representing equivalent words and phrases in a second language. These other signals are applied to a loudspeaker and are audibly perceived as speech in the second language.

Abstract: A global speech user interface (GSUI) comprises an input system to receive a user's spoken command, a feedback system along with a set of feedback overlays to give the user information on the progress of his spoken requests, a set of visual cues on the television screen to help the user understand what he can say, a help system, and a model for navigation among applications. The interface is extensible to make it easy to add new applications.

Abstract: Disclosed herein is an information processing device including: a data acquirer configured to acquire a sentence collection having a plurality of sentences and a plurality of phrases included in the sentence collection; a phrase feature decider configured to decide phrase features each representing a characteristic of a respective one of the phrases acquired by the data acquirer; a collection feature decider configured to decide a collection feature representing a characteristic of the sentence collection; and a compressor configured to generate compressed phrase features by using the phrase features and the collection feature, the compressed phrase features having a dimension lower than a dimension of the phrase features and each representing a characteristic of the respective one of the phrases acquired by the data acquirer.

Abstract: The present invention is a keyword display system that includes a speaker specifier for specify a speaker; a weight determinator for determining a weight of the specified speaker; a keyword extractor for extracting keywords from a speech of the aforementioned speaker; a keyword relation degree calculator for calculating a relation degree between the aforementioned extracted keywords, carrying out a weighting for this calculated relation degree by using the weight of the speaker having spoken the aforementioned keywords, and calculating a keyword relation degree between the keywords; and a keyword display controller for displaying a relevancy between the aforementioned extracted keywords responding to the aforementioned keyword relation degree.

Abstract: A translation apparatus capable of producing an optimal translation of an input sentence is provided.

Abstract: In a method of adapting communications in a communication system comprising at least two terminals (1,2), a signal carrying at least a representation of at least part of an information content of an audio signal captured at a first terminal (1) and representing speech is communicated between the first terminal (1) and a second terminal (2). A modified version of the audio signal is made available for at the second terminal (2). At least one of the terminals (1,2) generates the modified version by re-creating the audio signal in a version modified such that at least one prosodic aspect of the represented speech is adapted in dependence on input data (22) provided at at least one of the terminals (1,2).

Abstract: Embodiments are disclosed for automatically generating a banner given a first scroll sentence and a second scroll sentence of a Chinese couplet. The first and/or second scroll sentence can be generated by an automatic computer system or by a human (e.g., manually generated and then provided as input to an automated banner generation system) or obtained from any source (e.g., a book) and provided as input. In one embodiment, an information retrieval process is utilized to identify banner candidates that best match the first and second scroll sentences. In one embodiment, candidate banners are automatically generated. In one embodiment, a ranking model is applied in order to rank banner candidates derived from the banner search and generation processes. One or more banners are then selected from the ranked banner candidates.

Abstract: A method comprising a preliminary automated analysis of at least one corpus of natural language text is disclosed. For each sentence of a corpus, the method includes performing a syntactic analysis using linguistic descriptions to generate at least one syntactic structure for the sentence, building a semantic structure for the sentence, associating each generated syntactic and semantic structure with the sentence, and saving each structure. For each corpus text that was preliminary analyzed, performing an indexing operation to index lexical meanings and values of linguistic parameters of each syntactic structure and each semantic structure associated with sentences in the corpus text. A semantic search includes at least one automatic preliminary analyzed corpus of sentences comprising searched values of linguistic, syntactic and semantic parameters.

Abstract: A system and method for automatically generating sentences in a language is disclosed. The system comprising a grammar processor for converting an input grammar into a hierarchical representation, and a grammar explorer module for traversing the grammar hierarchy based on an explore specification, which defines what nodes of the hierarchy should be explored. The explorer module takes the exploration specification as input and traverses the hierarchy according to the exploration types specified in the exploration specification. The system and method can be used to automatically generate assembly instructions for a microprocessor given its assembly language grammar, to generate sentences of a natural language like English from its grammar and to generate programs in a high-level programming language like C.

Abstract: A system and method for presenting and editing associations between graphics and audio useful for assisting people who have difficulty in speaking. This may include presenting graphics and audio information together with topic information thus allowing for a user to create outlines of speech needed for different events and situations. When a user selects a topic, images appear and by selecting the image a device is instructed to play the associated audio file. Images and audio may be outlined into useful constructs to provide for differing situations and multiple users may edit those outlines. Moreover, the constructs, may be published to devices and other systems. In accordance with certain embodiments, images and audio files may be uploaded or purchased from vendors. Collaboration provides the speech impaired with the ability to develop a progressively improving speech vocabulary and to share that vocabulary with others needing assistance.

Abstract: An adaptive learning system and method provides for automatically generating question types to a user for word comprehension and selecting multiple choice answers for display. Questions are developed for the user by obtaining online content and indexing the content into individual sentences and questions. The system provides questions in a series of rounds to the user and then adaptively tracks the progress of the user based on the categorization of each question.

Abstract: A method for analyzing a telephonic communication between a customer and a contact center is provided. According to the method, a telephonic communication is separated into at least first constituent voice data and second constituent voice data. One of the first and second constituent voice data is analyzed by mining the voice data and applying a predetermined linguistic-based psychological behavioral model to one of the separated first and second constituent voice data. Behavioral assessment data is generated which corresponds to the analyzed voice data.

Abstract: The present disclosure discloses a method and apparatus of selecting a word sequence for a text written in a language without word boundary in order to solve the problem of having excessively large computation load when selecting an optimal word sequence in existing technologies. The disclosed method includes: segmenting a segment of the text to obtain different word sequences; determining a common word boundary for the word sequences; and performing optimal word sequence selection for portions of the word sequences prior to the common word boundary. Because optimal word sequence selection is performed for portions of word sequences prior to a common word boundary, shorter independent units can be obtained, thus reducing computation load of word segmentation.

Abstract: The present invention provides a topic transition analysis system that determines a position on a primary media stream leading to a certain statement made in a language communication carried out in a secondary channel associated with the primary media stream. The topic transition analysis system includes a statement trigger string determination unit receiving a primary media stream and one or a plurality of language communication streams (hereinafter, language streams) executed in parallel with the media stream and determining whether or not a certain statement on the one or plurality of language streams has been made newly in response to contents of the media stream.

Abstract: A syntactic analysis and hierarchical phrase model based machine translation system and method are provided. The machine translation system includes a word alignment module, a phrase extraction module, a gender syntactic annotation module, a syntactic based noncontiguous phrase abstract module, a noncontiguous phrase based translation module and an evaluation module. The machine translation system and method performs syntactic analysis based on a common contiguous phrase based machine translation model, and extracts a syntactic based noncontiguous phrase rule set from a bilingual aligned text, so as to address and issue of noncontiguous fixed custom in context of a whole sentence, and to comply with syntactic features of a language, translation is performed based on the noncontiguous phrase rule set and the phrase aligned table, and the translation results are evaluated based on the evaluation model, thereby improving the translation result.

Abstract: A multilingual multipoint videoconferencing system provides real-time translation of speech by conferees. Audio streams containing speech may be converted into text and inserted as subtitles into video streams. Speech may also be translated from one language to another, with the translated speech inserted into video streams as and choose the subtitles or replacing the original audio stream with speech in the other language generated by a text to speech engine. Different conferees may receive different translations of the same speech based on information provided by the conferees on desired languages.

Abstract: Methods and apparatus for audio watermarking a substantially silent media content presentation are disclosed. An example method to audio watermark a media content presentation disclosed herein comprises obtaining a watermarked noise signal comprising a watermark and a noise signal having energy substantially concentrated in an audible frequency band, the watermarked noise signal attenuated to be substantially inaudible without combining with a separate audio signal, associating the watermarked noise signal with a substantially silent content component of the media content presentation, the media content presentation comprising one or more media content components, and outputting the watermarked noise signal during presentation of the substantially silent content component.

Abstract: In some embodiments, a non-transitory processor-readable medium stores code representing instructions that when executed cause a processor to select a narrative content template based at least in part on a predetermined content type associated with a real-world and/or virtual event. The code further represents instructions that when executed cause the processor to select a narrative tone type. The code further represents instructions that when executed cause the processor to, for each phrase included in an ordered set of phrases associated with the narrative content template, select, based at least in part on the narrative tone type, a phrase variation from a set of phrase variations associated with that phrase, and define, based on the selected phrase variation and at least one datum from a set of data, a narrative content portion associated with the real-world event. The code further represents instructions that when executed cause the processor to output, at a display, the narrative content portion.

Abstract: An apparatus for classifying documents (5) based on sound includes a document transport (30) for transporting a document; an audio transducer (20) for detecting a sonic profile produced by the document as it is transported; and a controller for determining document characteristics based on the sonic profile.

Abstract: Methods, systems, and apparatus, including computer program products, to identify topic words in a collection of documents that includes topic documents related to a topic are disclosed. A reference topic word divergence value based on a document collection and the topic document collection is determined. A candidate topic word divergence value for a candidate topic word is determined based on the document collection and the topic document collection. The candidate topic word is determined to be a topic word if the candidate topic word divergence value is greater than the reference topic word divergence value.

Abstract: A general digital semantic database for mechanical language translation is provided. The database has vocabulary decomposed to part of speech characteristics and semantic characteristics to form inseparable basic semantic points. The vocabulary is regularly ordered according to classes of the semantic characteristic, part of speech characteristic, background and grammatical relation. Two or more languages are configured on the basic semantic points according to a synonymies relation. The languages are discretionarily interchanged based on the basic semantic points by a machine. The languages semantemes and syntax relation formula are configured in the semantic database to realize an automatic paginal translation.

Abstract: A translation method and device (1) enabling a first individual speaking in a first language to converse with a second individual speaking in a second language different from the first language, the device includes translation element (30) translating the first words of the first individual into the second language and the second words of the second individual into the first language. The device is provided with a headset (12) connected to the translation element (30) by connection element (20), the headset (12) being provided with at least one earpiece (11, 11?), a microphone (14), and a loudspeaker (15), the microphone (14) picking up first and second words from the first and second individuals in order to enable the first and second words to be translated by the translation element (30) and then, once translated, to be delivered respectively to the earpiece (11, 11?) or to the loudspeaker (15).

Abstract: The present invention concerns a method and a system for integrating voice inputs to a three-dimensional virtual application software, such as a game, on at least one computer during the execution of said virtual application software on said at least one computer, said system comprising: voice receiving means for receiving a voice input signal real-time sound streaming means, such as an application programming interface (API), receiving at least one external voice input from a user, wherein said voice audio input is encoded to an intermediate output voice sound stream; three-dimensional software application means comprising means adapted for subjecting said intermediate output voice sound stream data to predetermined software application logic defined in the application software, including identifying the game state of the user in the application software; output audio data stream generating means for manipulating output voice stream data and any activity related application software generated sounds, wherein

Abstract: A system and method for automatically generating patient-specific and grammatically correct electronic medical records is disclosed. The system and method of an example embodiment includes retrieving a statement from a data object, the data object including the statement, at least one response option corresponding to the statement, and at least one sentence fragment corresponding to the response option; generating, using a processor, a user interface view that includes the statement; receiving a response corresponding to the statement; correlating the response to the at least one response option; retrieving the sentence fragment that corresponds to the correlated response option; and generating, using the processor, a patient-specific and grammatically correct electronic medical record using the retrieved sentence fragment.

Abstract: A display section displays an obtained character-string written in a first language. A translation unit extraction section divides the obtained character-string into predetermined translation units, and extracts a character-string for each translation unit. A translation unit translates the extracted character-strings in the translation units into a second language. A display control section displays, on the display section, the result of translation by the translation section from the head of the character-string being displayed, in a state of being associated with the character-string.

Abstract: Method and apparatus for capturing a text based source image 5, 5A provided on an object 3 supported on a surface. Positioned above the object 3 is a camera 7 for capturing a view of the text based image 5, 5A. The camera 7, through lens 9 generates a focused image of at least part of the object 3 and transmits this image to a processor 11 for magnification of the image captured by the camera 7 to a size specified for display on a display device 15. In the processor 11 the magnification is effected to a rate that is controlled by the second predefined size for display 19, 19A of the font to appear on the display 15 and is independent of the first font size.

Abstract: Systems, methods, and apparatus for identifying and classifying noise of an intracardiac electrogram of a cardiac rhythm management device to prevent inaccurate detection of a cardiac episode are disclosed. In an example, three channels are analyzed to identify and determine whether an episode or noise has been detected.

Abstract: Systems and methods are provided for providing a score for a spontaneous non-native speech response to a prompt. A transcription of the spontaneous speech response is accessed. A plurality of clauses are identified within the spontaneous speech response, where identifying a clause includes identifying a beginning boundary and an end boundary of the clause in the spontaneous speech response. A plurality of disfluencies in the spontaneous speech response is identified. One or more proficiency metrics are calculated based on the plurality of identified clauses and the plurality of the identified disfluencies, and a score for the spontaneous speech response is generated based on the one or more proficiency metrics.

Abstract: Packet loss concealment (PLC) systems and methods are described that use time-warping to merge a concealment signal generated to replace one or more bad frames of an audio signal with a received signal representing one or more subsequent good frames of the audio signal in a manner that avoids signal discontinuity and audible artifacts resulting therefrom. Prediction-based PLC systems and methods are also described that use time-warping to conceal the loss of one or more frames containing a transition region in a manner that will not result in an audible artifact.

Abstract: An interactive language training system allows practice word/phrase lists customized by the user for training. The customized lists may include words/phrases extracted from content sources based upon user selections. Extraction may include analysis of the content sources to determine word/phrase frequency, topic, and/or other parameters. A video sample of a student speaking a word/phrase is compared with video examples of a speaker and provides visual feedback for pronunciation and articulation. Progress is monitored for each word/phrase on the list, and performance feedback provided. Communication, such as voice or video chat may be established between the student and a speaker to provide for additional practice.

Abstract: The present invention provides a method for generating derivative words including the steps of: creating a number of derivative grammar arrays; matching the inputting character information with the derivative grammar arrays and obtaining the match derivative grammar arrays; obtaining match words from the language database according to the condition arrays of the obtained derivative grammar arrays and the inputting character information; and generating derivative words by adding the suffix alphabetic character sets of the obtained derivative grammar arrays to the ends of the words. In accordance with the established grammar rules, the words in the language database can be converted to derivative words and the derivative words do not need to be stored in the language database. Therefore, the storage space of the language database can be remarkably reduced. The present invention also provides a system for generating derivative words.

Abstract: A method and apparatus for automatically detecting sentiment in interactions. The method and apparatus include training, in which a model is generated upon features extracted from training interactions and tagging information. and run-time in which the model is used towards detecting sentiment in further interactions. The method and apparatus train and use models for classifying context units as containing sentiment or not, the models generated upon tagging data for indicating whether the context units indeed contain sentiment, and the sentiment polarity and intensity within the context unit. A further, upper level model is generated for providing a total score for the interaction, based on the sentiment detected and the classification scores of context units within the interaction.

Abstract: The present invention generally relates to a voice-based command driven computer implemented method and programmed apparatus that allows a user to easily add any open API communication product they choose to one interface. The computer implemented method filters all electronic communications selected by the user through a common source, such as the user's cell phone or computer. Each time an electronic communication is received, no matter through what program or application, the computer implemented method operates to communicate to the user that the electronic communication has been received and provides the user with the option of listening to and responding to the electronic communication, if appropriate. The user responds to the electronic communication through voice-based communication rather than physical interaction with the common source. The user may additionally initiate electronic communication through voice-based communication.

Abstract: A method and apparatus for automating the acquisition, reconstruction, and generation of knowledgebases of associated ideas and using such knowledgebases in many application including machine translation of human languages, search and retrieval of unstructured text, or other data, based on concept search, voice recognition, data compression, and artificial intelligence systems.

Abstract: An apparatus and method are disclosed for providing feedback and guidance to touch screen device users to improve the text entry user experience and performance through the use of indicators such as feedback semaphores. Also disclosed are suggestion candidates, which allow a user to quickly select next words to add to text input data, or replacement words for words that have been designated as incorrect. According to one embodiment, a method comprises receiving text input data, providing an indicator for possible correction of the text input data, displaying suggestion candidates associated with alternative words for the data, receiving a single touch screen input selecting one of the suggestion candidates, and modifying the input data using the word associated with the selected suggestion candidate.

Abstract: A method for mimicking the auditory system's response to rhythm of an input signal having a time varying structure comprising the steps of receiving a time varying input signal x(t) to a network of n nonlinear oscillators, each oscillator having a different natural frequency of oscillation and obeying a dynamical equation of the form r . = r ? ( ? + ? 1 ? ? z ? 2 + ? ? ? 2 ? ? z ? 4 1 - ? ? ? z ? 2 ) + c ? ? x ? ( t ) ? cos ? ? ? - r ? ? ? ? ? r 2 - 2 ? ? ? r ? ? cos ? ? ? + 1 ? . = ? + ? 1 ? r 2 + ? ? ? 2 ? r 4 1 - ? ? ? r 2 - c ? ? x ? ( t ) ? sin ? ( ? ) ? ? ? r 2 - 2 ? ? ? r ? ? cos ? ( ? ) + 1 ? ? ? . = - k ? ? x ? ( t ) ? sin ? ? ? ? ? ? r 2 - 2 ? ? ? r ? ? cos ? ? ? + 1 wherein ? represents the response frequency, r is the amplitude of the oscillator and ? is the phase of the oscillator.

Abstract: A method and apparatus for automating the acquisition, reconstruction, and generation of knowledgebases of associated ideas and using such knowledgebases in many application including machine translation of human languages, search and retrieval of unstructured text, or other data, based on concept search, voice recognition, data compression, and artificial intelligence systems.

Abstract: A method and apparatus for automating the acquisition, reconstruction, and generation of knowledgebases of associated ideas and using such knowledgebases in many application including machine translation of human languages, search and retrieval of unstructured text, or other data, based on concept search, voice recognition, data compression, and artificial intelligence systems.

Abstract: A method of operation of a remote controller consistent with certain implementations involves determining a spatial orientation of the remote controller based upon an output signal from a position detector; and setting a voice mode of operation of the remote controller as active or inactive based upon the spatial orientation of the remote controller as determined by the position detector, where the voice mode determines whether or not the remote controller will accept and process voice information from a microphone. This abstract is not to be considered limiting, since other embodiments may deviate from the features described in this abstract.

Abstract: The invention provides a system and method for improving speech recognition. A computer software system is provided for implementing the system and method. A user of the computer software system may speak to the system directly and the system may respond, in spoken language, with an appropriate response. Grammar rules may be generated automatically from sample utterances when implementing the system for a particular application. Dynamic grammar rules may also be generated during interaction between the user and the system. In addition to arranging searching order of grammar files based on a predetermined hierarchy, a dynamically generated searching order based on history of contexts of a single conversation may be provided for further improved speech recognition.

Abstract: A method of controlling a system which includes the steps of obtaining at least one signal representative of information communicated by a user via an input device in an environment of the user, wherein a signal from a first source is available in a perceptible form in the environment; estimating at least a point in time when a transition between information flowing from the first source and information flowing from the user is expected to occur; and timing the performance of a function by the system in relation to the estimated time.

Abstract: A method for remote video communication, the method including gathering a library of video images of a user, selecting a scenario of communication with an interlocutor, selecting a video image of the user, presenting the video image to the interlocutor, protecting the video image from the interlocutor by defining a degree of a correction, tracing and recognizing characteristic features of a behavior of the interlocutor, defining an emotional state of the user, correcting the emotional state of the user, defining the degree of the correction of the video image of the interlocutor, and providing the video image with a realistic appearance.

Abstract: This invention is a system and method for incrementally and multi-dimensionally adjusting prose style. It comprises: a prose input interface, through which the user inputs, or otherwise selects, prose; a multi-dimensional style-adjusting interface, through which the user incrementally adjusts multiple dimensions of prose style; and a style-morphing engine which executes the adjustments specified by the user through the multi-dimensional style-adjusting interface. The dimensions of prose style to be adjusted may be selected from the group consisting of: person perspective; tense; voice; length; vocabulary; formality; colloquiality; complexity; emotion; emoticons; color; font; romantic; positivity; strength; precision; certainty; alliteration; humor; nationality; regionality; gender specificity; obscenity filter; academic jargon; business jargon; legal jargon; medical jargon; scientific jargon; and connectivity jargon.

Abstract: Disclosed is an on demand, web-based, outbound contact center utilizing Voice over IP (VoIP) and speaker-independent voice recognition which automatically captures contact responses to question events in a pre-recorded, interactive voice call, the call launched by a user via a broadcast comprising a call sequence created by the user via a call center user interface comprising event add and logic add wizards, the call sequence comprising event prompts based on a user-generated script comprising message events and question events, the event prompts in the group consisting of voice recordings and text-to-speech inputs.

Abstract: A computer program product for communicating across channels with emotion preservation includes a computer usable storage medium having computer useable program code embodied therewith, the computer usable program code including: computer usable program code to receive a first language communication comprising text marked up with emotion metadata; computer usable program code to translate the emotion metadata into second language emotion metadata; computer usable program code to translate the text to second language text; computer usable program code to analyze the second language emotion metadata for second language emotion information; and computer usable program code to combine the second language emotion information in first language communication with the second language text.

Abstract: A computer implemented method used to interpret text, including from a set of formal glossaries which may refer one to the other and are intended to define precisely the terminology of a field of endeavor. Such glossaries are known as intelligent, in the sense that they allow machines to make deductions, without the need for human intervention. However, they may also accept human intervention. Once a word is defined in an intelligent glossary, all the logical consequences of the use of that word in a formal and well-formed sentence are computable. The process includes a question and answer mechanism, which applies the definitions contained in the intelligent glossaries to a given formal sentence. The methods may be applied in the development of knowledge management methods and tools that are based on semantics; for example: modeling of essential knowledge in the field based on the relevant semantics.

Abstract: A voice recognition device includes a voice input unit 11 for inputting a voice of an uttered button name to convert the voice into an electric signal, a voice recognition processing unit 12 for performing a voice recognition process according to a sound signal sent thereto, as the electric signal, from the voice input unit, a button candidate detecting unit 13 for detecting, as a button candidate, a button having a button name which partially matches a voice recognition result acquired by the voice recognition processing unit, a display control unit 15 for, when a plurality of candidate buttons are detected by the button candidate detecting unit, producing a screen showing a state in which at least one of the plurality of button candidates is selected, and a display unit 16 for displaying the screen produced by the display control unit.