Abstract: A language interpretation system receives a request for an interpretation of a voice communication between a first language and a second language. Further, the language interpretation system provides the request to a machine language interpreter. In addition, the machine language interpreter provides live language interpretation of the voice communication. The live language interpretation of the voice communication is halted by the machine language interpreter in real time during the live language interpretation based upon a criteria being met. Further, the voice communication is transitioned to a human language interpreter to resume the live language interpretation of the voice communication after the machine language interpreter is halted.

Abstract: Methods and systems for setting selected automatic speech recognition parameters are described. A data set associated with operation of a speech recognition application is defined and includes: i. recognition states characterizing the semantic progression of a user interaction with the speech recognition application, and ii. recognition outcomes associated with each recognition state. For a selected user interaction with the speech recognition application, an application cost function is defined that characterizes an estimated cost of the user interaction for each recognition outcome. For one or more system performance parameters indirectly related to the user interaction, the parameters are set to values which optimize the cost of the user interaction over the recognition states.

Abstract: A voice activated system for operating electronic devices in an environment includes a microphone for receiving a verbal command that requests the addition of a new voice command, a first processor, that is electrically connected to the microphone, for receiving a customized command input regarding a preexisting user for the voice activated system that should be associated with the new verbal command, input involving a new verbal command, and input involving a system command, where the first processor is then able to receive verbal input to recognize a user, a verbal command, and then determine an associated action, an appropriate command for that action and then generate an associated system command, and a second processor, in electronic communication with the first processor, and two or more electronic devices in an environment, where the second processor is capable of receiving the system command and operating the two or more devices.

Abstract: A computer program product is provided and includes a non-transitory tangible storage medium readable by a processing circuit and on which instructions are stored for execution by the processing circuit for performing a method. The method includes enabling retrieval of a keyboard pressed sequence of characters of a first type, permitting a re-selection of characters of a second type, which are associated with the keyboard pressed sequence of the characters of the first type and permitting modification of the keyboard pressed sequence of the characters of the first type to initiate a search for and retrieval of characters of the second type.

Abstract: Converting technical data from field oriented electronic data sources into natural language form is disclosed. An approach includes obtaining document data from an input document, wherein the document data is in a non-natural language form. The approach includes determining a data type of the document data from one of a plurality of data types defined in a detection and conversion database. The approach includes translating the document data to a natural language form based on the determined data type. The approach additionally includes outputting the translated document data in natural language form to an output data stream.

Abstract: Sound related vehicle information representing one or more sounds may be received in the processor. The sound related vehicle information may or may not include an audio signal. Spoken dialogue of a spoken dialogue system associated with the vehicle based on the sound related vehicle information may be modified.

Abstract: A voice activated translation device comprising: a housing, where the housing comprises, a microprocessor to translate a message; a screen to display one or more languages to be translated; a speaker positioned by the screen, where the speaker plays a translated message; a microphone positioned by the speaker, where the microphone receives the message to be translated; and a plurality of buttons positioned on the housing, where the plurality of buttons operate the housing; and an earpiece worn by a first user, where the earpiece comprises, an earbud to enable the first user to hear the translated message; a hook to securely attach the earpiece to the first user's ear; and a mouthpiece, where the mouthpiece receives the message to be translated. The voice activated translation device processes and plays translated messages to enable people of different speaking languages to converse.

Abstract: Natural language processing (‘NLP’) including: receiving text specifying predetermined evidence; receiving a text passage to process, the text passage including conditions and logical operators, the text passage comprising criteria for evidence; decomposing the text passage into coarse grained text fragments, including grouping text segments in dependence upon the logical operators; analyzing each coarse grained text fragment to identify conditions; evaluating each identified condition in accordance with the predetermined evidence and predefined condition evaluation rules; evaluating each coarse grained text fragment in dependence upon the condition evaluations and the logical operators; and calculating, in dependence upon the evaluations of each text fragment, a truth value indicating a degree to which the evidence meets the criteria of the text passage.

Abstract: A system, method, and computer-readable medium, is described that implements a domain name registration suggestion tool that receives one or more inputs, extracts information from the inputs into a submission string, submits the submission string to a domain name suggestion tool, and receives domain name suggestions based on the submission string. Inputs types may include images, audio clips, and metadata. The inputs sources may be processed to extract information related to the image source to build the submission string.

Abstract: The present invention is related to a social system and process used for bringing virtual social network into real life, which is allowed for gathering and analyzing a social message of at least one interlocutor from virtual social network so as to generate at least one recommended topic, allowing a user to talk with the interlocutor through the utilization of the recommended topic, and then capturing and analyzing at least one speech and behavior and/or physiological response of the interlocutor during talking so as to generate an emotion state of the interlocutor. The user is allowed to determine whether the interlocutor is interested in the recommended topic through the emotion state of interlocutor. Thus, it is possible to bring the social message on virtual network into real life, so as to increase communication topics between persons in real life.

Abstract: A message within a message queue can be identified. The message queue can be within a software entity of a computing device. The message can be analyzed to determine an encoding scheme to apply to the message. The message can be encoded using the encoding scheme to create an encoded message. The encoding scheme can be a word level encoding scheme, a language-based encoding scheme, or a grammar encoding scheme.

Abstract: Methods, systems, and computer programs are presented for linking newsworthy events in a document to published content. One method includes an operation for receiving features by a classifier that is operable to determine a probability of the availability of news for a sentence. When the features are found in the sentence, the probability of the availability of news for the sentence increases, where the sentence includes one or more noun phrases and ends in a full stop. The classifier determines which sentences in a document are candidate sentences for being linked to news articles, and for each candidate sentence, the method includes an operation for finding an associated news article when there is an associated news article exceeding a relevance threshold. Further, the method includes operations for adding links in the document to the found associated news articles, and for displaying the document with the added links.

Abstract: Systems and methods are provided for detecting and analyzing speech spoken in the vicinity of a user. The detected speech may be analyzed to determine the quality, volume, complexity, language, and other attributes. A value metric may be calculated for the received speech, such as to inform parents of a child's progress related to learning to speak, or to provide feedback to a foreign language learner. A corresponding device may display the number of words, the value metric, or other information about speech received by the device.

Abstract: A user device communicates with a network server that has access to one or more knowledge sources. Based on a current situational context for a user of the device, the network server dynamically generates a group-related personalized dictionary using information retrieved from the knowledge sources and provides the dictionary to the user device. Applications executing on the user device can then use the dictionary to suggest or predict words, terms, or symbols to the user in response to receiving user input.

Abstract: A technique is presented for fast input of multi-character compound consonants and vowels on a touch computing device. The technique provides for fast input of multi-character compound consonants and vowels by enabling a user to touch an initial character on a first layout of characters, then slide his/her finger in different directions and/or different distances according to a second layout of characters. The second layout of characters can be based on the first touched character and therefore can have a limited set of characters, e.g., fewer characters in comparison to the first layout of characters. A syllable formed after input of both a consonant and a vowel, represented as one character set, e.g., in the Roman alphabet, can then be transliterated into another language, e.g., Chinese.

Abstract: An apparatus and method for including emotional context in textual electronic communication transmissions. The emotional context is conveyed symbolically through standardized alternations in the manner in which the text is displayed without the inclusion of additional graphics, thereby increasing the communicative value of textual electronic communication. An important advantage of this method of embedding emotional context is that the recipient is made aware of the mental and emotional state of to the originator while the textual electronic message is being received and interpreted and therefore is able to interpret the message in light of the emotional context.

Abstract: A vehicle communication system is provided and may include at least one communication device that audibly communicates information within the vehicle. A controller may receive a character string from an external device and may determine if the character string represents an emoticon. The controller may translate the character string into a face description if the character string represents an emoticon and may audibly communicate the face description via the at least one communication device.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for processing multimodal input. A system configured to practice the method continuously monitors an audio stream associated with a gesture input stream, and detects a speech event in the audio stream. Then the system identifies a temporal window associated with a time of the speech event, and analyzes data from the gesture input stream within the temporal window to identify a gesture event. The system processes the speech event and the gesture event to produce a multimodal command. The gesture in the gesture input stream can be directed to a display, but is remote from the display. The system can analyze the data from the gesture input stream by calculating an average of gesture coordinates within the temporal window.

Abstract: The preferred embodiments of this invention convert common human speeches into rap music. Computer programs change the timing intervals, amplitudes, and/or frequencies of the sound signals of a common speech to follow rap music beats. The resulting rap music also can overlap with background music and/or video images to achieve better effects.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for presenting a machine translation and alternative translations to a user, where a selection of any particular alternative translation results in the re-ranking of the remaining alternatives. The system then presents these re-ranked alternatives to the user, who can continue proofing the machine translation using the re-ranked alternatives or by typing an improved translation. This process continues until the user indicates that the current portion of the translation is complete, at which point the system moves to the next portion.

Abstract: An apparatus and method providing a localization framework capable of localizing dynamic text is disclosed herein. The localization framework is configured to automatically identify and prioritize certain text contained within an application code base to be translated. Such text is pre-processed prior to translation to facilitate accurate and complete translation in a target language.

Abstract: Described are computer-based methods and apparatuses, including computer program products, for automated content generation. In some examples, the method includes generating content metadata from document content via natural language processing based on one or more context parameters associated with the document content. The method can further include receiving user feedback about the content metadata from a computing device associated with a user associated with the document content. The method can further include modifying the one or more context parameters based on the received user feedback.

Abstract: A method, an apparatus, and a computer program product for contextual-based search of modeling notations to be used in a model. The method comprises obtaining a contextual property of a notation to be used in a diagram, wherein the contextual property defines a context of a usage of the notation in the diagram; and searching in a notation-base for notations, whereby a search result set is obtained, wherein the search result set comprises notations that were previously used in a similar context to the contextual property, wherein the notation-base is stored in a data storage.

Abstract: A speech recognition engine is provided voice data indicative of at least a brand of a target appliance. The speech recognition engine uses the voice data indicative of at least a brand of the target appliance to identify within a library of codesets at least one codeset that is cross-referenced to the brand of the target appliance. The at least one codeset so identified is then caused to be provisioned to the controlling device for use in commanding functional operations of the target appliance.

Abstract: A system and method are disclosed for activating an electric device from a standby power mode to a full power mode. The system may include one or more microphones for monitoring audio signals in the vicinity of the electric device, and a standby power activation unit including a low-power microprocessor and a non-volatile memory. Audio captured by the one or more microphones is digitized and compared by the microprocessor against predefined activation pattern(s) stored in the non-volatile memory. If a pattern match is detected between the digital audio pattern and a predefined activation pattern, the electric device is activated.

Abstract: A method to display multiple language characters is provided. The method comprises a number of steps. A multiple language character data is stored. The multiple language character data comprises a common character part and a plurality of offset parts. The common character part comprises a plurality of common characters and each of the offset parts comprises a plurality of specific language characters. A selection command is received. One of the offset parts is retrieved according to the selection command. At least one character is displayed on a display module according to the common character part and the selected offset part.

Abstract: Techniques for providing a translation environment interface to a user are disclosed herein. The techniques include receiving a message template to be translated, the message template including a text portion and one or more template placeholders, parsing the message template to identify the text portion and the template placeholders, generating non-editable objects corresponding to the template placeholders and generating a display message template by replacing each of the one or more template placeholders with its corresponding non-editable object in the message template, the display message template including the text portion to be translated. The techniques further include providing the display message template to a user device and receiving a translated display message template from the user device, the translated message including a translated text portion and the one or more non-editable objects.

Abstract: An automatic language-processing system uses a human-curated lexicon to associate words and word groups with broad sentiments such as fear or anger, and topics such as accounting fraud or earnings projections. Grammar processing further characterizes the sentiments or topics with logical (“is” or “is not”), conditional (probability), temporal (past, present, future), quantitative (larger/smaller, higher/lower, etc.), and speaker identification (“I” or “He” or “Alan Greenspan”) measures. Information about the characterized sentiments and topics found in electronic messages is stored in a database for further analysis, display, and use in automatic trading systems.

Abstract: Aspects for teaching processing linguistic expressions are disclosed, which include apparatuses, methods, and computer-readable storage media to facilitate such processing. In a particular aspect, modifying a linguistic expression includes receiving an input that includes the linguistic expression and a selection of a target vernacular, and retrieving a phonetic scheme corresponding to the target vernacular, which includes a set of accentuation rules associated with the target vernacular. An audible equivalent of the linguistic expression is then generated in the target vernacular according to the phonetic scheme. In another aspect, phonetic schemes are generated by aggregating linguistic information corresponding to a plurality of vernaculars, and analyzing the linguistic information to ascertain a plurality of accentuation rules. A phonetic scheme is then generated for each of the plurality of vernaculars, which includes a set of accentuation rules associated with the corresponding vernacular.

Abstract: A computing device (e.g., a smart phone, a tablet computer, digital camera, or other device with image capture functionality) causes an image capture device to capture one or more digital images based on audio input (e.g., a voice command) received by the computing device. For example, a user's voice (e.g., a word or phrase) is converted to audio input data by the computing device, which then compares (e.g., using an audio matching algorithm) the audio input data to an expected voice command associated with an image capture application. In another aspect, a computing device activates an image capture application and captures one or more digital images based on a received voice command. In another aspect, a computing device transitions from a low-power state to an active state, activates an image capture application, and causes a camera device to capture digital images based on a received voice command.

Abstract: Provided in some embodiments is a computer implemented method that includes providing script data including script words indicative of dialogue words to be spoken, providing audio data corresponding to at least a portion of the dialogue words to be spoken, wherein the audio data includes timecodes associated with dialogue words, generating a sequential alignment of the script words to the dialogue words, matching at least some of the script words to corresponding dialogue words to determine alignment points, determining corresponding timecodes for unmatched script words using interpolation based on the timecodes associated with matching script words, and generating time-aligned script data including the script words and their corresponding time codes.

Abstract: Various embodiments provide summarization techniques that can be applied to blogs or microblogs to present information that is determined to be useful, in a shortened form. In one or more embodiments, a procedure is utilized to automatically acquire a set of concepts from various sources, such as free text. These acquired concepts are then used to guide a clustering process. Clusters are ranked and then summarized by incorporating sentiment and the frequency of words.

Abstract: Provided in some embodiments is a method including receiving ordered script words are indicative of dialogue words to be spoken, receiving audio data corresponding to at least a portion of the dialogue words to be spoken and including timecodes associated with dialogue words, generating a matrix of the ordered script words versus the dialogue words, aligning the matrix to determine hard alignment points that include matching consecutive sequences of ordered script words with corresponding sequences of dialogue words, partitioning the matrix of ordered script words into sub-matrices bounded by adjacent hard-alignment points and including corresponding sub-sets the script and dialogue words between the hard-alignment points, and aligning each of the sub-matrices.

Abstract: Techniques and solutions are provided for adaptive input language switching. Automatic switching of a current input language can be performed by receiving an indication of a first language of displayed content (where the current input language is set to a second language different from the first language), receiving a selection of a text input area, and based on the selection, automatically switching the current input language from the second language to the first language. Switching of the current input language can also be performed by providing convenient user interface elements for selection by a user to automatically switch the current input language.

Abstract: A collaborative language translation system, computer readable storage medium, and method is disclosed that allocates as between automated and manual language translation services, wherein a manual language translator creates a unique database including manual translator languages capability, accuracy skill level, scope of translation project desired, and translation turnaround time. Also a client creates a unique information set that includes original language, desired language, scope of translated material, client desired translation formats, client desired translation timing, and client desired translation accuracy. Also included in the system is an automated language translation database and instructions for allocating a flow of the unique information set as between the unique database and the automated language translation database based upon the client unique information set and instructions to perform the selected language translation for the client.

Abstract: An online monitoring system assists parents or other individuals in monitoring social networking activity and/or mobile phone usage of their children or others. The online monitoring system may gather data corresponding with monitored social networking and/or mobile phone accounts. The data may be analyzed to provide summarized information and alert notifications to parents or other individuals. The analyses provided by the online monitoring service may include several text-based analyses: keyword analysis, sentiment analysis, and structure analysis. The keyword analysis may include analyzing text to determine whether it includes any blacklisted or whitelisted words. The sentiment analysis may include determining an overall sentiment of text based on the sentiment of words within the text. The structure analysis may include analyzing the sentence structure of the text to identify grammatical parts. An overall structure score is determined based on the sentiment of the grammatical parts.

Abstract: A method includes receiving script data including script words for dialogue, receiving audio data corresponding to at least a portion of the dialogue, wherein the audio data includes timecodes associated with dialogue words, generating a sequential alignment of the script words to the dialogue words, matching at least some of the script words to corresponding dialogue words to determine hard alignment points, partitioning the sequential alignment of script words into alignment sub-sets, wherein the bounds of the alignment sub-subsets are defined by adjacent hard-alignment points, and wherein the alignment subsets includes a sub-set of the script words and a corresponding sub-set of dialogue words that occur between the hard-alignment points, determining corresponding timecodes for a sub-set of script words in a sub-subset based on the timecodes associated with the sub-set of dialogue words, and generating time-aligned script data including the sub-set of script words and their corresponding timecodes.

Abstract: In example embodiments, a technique is provided to determine the similarity between two terms. For example, example embodiments may store a meta-model semantic network that includes a first and second term. Further, both the first and second terms are respectively associated with model and meta-model information. A request to calculate a term similarity value is received. A term similarity value expresses a correlation between the first term and the second term. The term similarity value is then calculated based on a comparison of the model and the meta-model information associated with the first and second terms.

Abstract: Methods for providing access to voice content are provided. For example, voice content is accessible to a plurality of users employing a platform in which inputting, outputting, searching, processing and transacting are facilitated in a manner uniquely suited to voice content. Such a platform may isolate characteristics specific to voices for purposes of ranking, grouping, gaming, translating, teaching or studying.

Abstract: The present invention discloses a method, apparatus and computer program product for determining the location of a plurality of speech sources in an area of interest, comprising performing an algorithm on a signal issued by either one of said plurality of speech sources in the area to for iteratively recover data characteristic to said signal, wherein the algorithm is an iterative model-based sparse recovery algorithm, and wherein for each of a plurality of points in said area, the iteratively recovered data is indicative of a presence of a plurality of speech sources contributing to the signal received at each of a plurality of points in the area.

Abstract: A multichannel security system is disclosed, which system is for granting and denying access to a host computer in response to a demand from an access-seeking individual and computer. The access-seeker has a peripheral device operative within an authentication channel to communicate with the security system. The access-seeker initially presents identification and password data over an access channel which is intercepted and transmitted to the security computer. The security computer then communicates with the access-seeker. A biometric analyzer—a voice or fingerprint recognition device—operates upon instructions from the authentication program to analyze the monitored parameter of the individual. In the security computer, a comparator matches the biometric sample with stored data, and, upon obtaining a match, provides authentication. The security computer instructs the host computer to grant access and communicates the same to the access-seeker, whereupon access is initiated over the access channel.

Abstract: The gaming and linguistic data generating technique described herein provides an online multiplayer game that can generate linguistic data, such as, for example, monolingual paraphrase data or multilingual parallel data, as a by-product of the game. The game is designed along the lines of sketch-and-convey paradigm. The game can be played as follows. A phrase is chosen from a phrase corpus and is given to one player (the “Drawer”) who then conveys it to the other player (the “Guesser”) by drawing a picture of the phrase. The Guesser guesses at the components of the phrase either in the same language as the phrase or possibly in a different language. If the Guesser's guesses converge to the chosen phrase, this generates monolingual paraphrases (if the game is played in the same language), and parallel text (if the game is played between multilingual players or two monolingual players in different languages).

Abstract: A method for providing suggestions includes capturing audio that includes speech and receiving textual content from a speech recognition engine. The speech recognition engine performs speech recognition on the audio signal to obtain the textual content, which includes one or more passages. The method also includes receiving a selection of a portion of a first word in a passage in the textual content, wherein the passage includes multiple words, and retrieving a set of suggestions that can potentially replace the first word. At least one suggestion from the set of suggestions provides a multi-word suggestion for potentially replacing the first word. The method further includes displaying, on a display device, the set of suggestions, and highlighting a portion of the textual content, as displayed on the display device, for potentially changing to one of the suggestions from the set of suggestions.

Abstract: A system to teach phonemic awareness uses a plurality of phonemes and a plurality of graphemes. Each phoneme is a unique sound and an indivisible unit of sound in a spoken language, and each grapheme is a written representation of one of the plurality of phonemes. A plurality of distinct graphical images and a plurality of unique names are provided where each unique name is associated with one of the graphical images and represents a grouping of graphemes selected from the plurality of graphemes. The system uses a plurality of sets of display pieces having a plurality of individual display pieces. Each individual display piece includes at least a portion of one of the graphical images and the graphemes from the grouping of graphemes constituting the associated unique name. A predefined instructional environment defines a predefined spatial context and predefined rules governing the acquisition and utilization of individual display pieces.

Abstract: An environmental condition detector emits only safe, validated verbal messages recorded in a user's voice to help occupants of a building respond safely to sensed environmental conditions. The message emitted in the user's voice is generally a familiar voice to other building occupants to better capture their attention, and only certain, safe, user messages are validated for use thereby eliminating the chance that the user may unknowingly record an unsafe message to be emitted during a sensed environmental condition. The verbal message is recorded by a user and is analyzed through speech recognition to determine if the user-recorded message can be validated as containing safe content. A user-recorded message found to match manufacturer preprogrammed message content is validated and selected to be audibly emitted in the user's voice when an environmental condition is sensed. Various embodiments include single station units, interconnected units, or centrally controlled security systems.

Abstract: A social networking system includes a mechanism for integrating user actions on objects outside of the social networking system in the social graph. External system operators include widgets that, when executed by user devices, record user interactions that correspond to a defined structure of actions and objects. Third party operators utilize a tool provided by the social networking system to define the structure of actions and objects, verb tenses of action types, and noun forms object types. External actions are recorded by the social networking system for publishing to the social graph in dynamically generated sentences formed using the structure of the actions and objects.

Abstract: A wireless extension device to end-user wireless device has a collar that is worn around the neck. The collar has two end-members that are positioned on the two collar bone areas next to the neck. The end-members have positioned directional speakers therein that radiate sound in the direction of two ears of the human wearing the collar around the neck. The end-members have positioned microphones that pick up voice commands of a human wearing the collar around the neck. The wireless collar extension device is used for hands free communication with end-user wireless device, without having to plug a prior art BLUETOOTH earpiece into one of the ears.

Abstract: An example method may include receiving a media stream from a first endpoint, where the media stream is intended for a second endpoint; processing the media stream according to at least one processing option; compressing the media stream; and communicating the media stream to the second endpoint. In more specific instances, the processing may include converting a speech in the media stream to text in a first language; converting the text in the first language to text in a second language; rendering the text in the second language; and adding the rendered text in the media stream.

Abstract: A voice-activated instrument performs a measurement and displays the measured value when commanded by voice. The system also resets under voice control. The measurement trigger is any single-syllable command such as “Count” or “Go”. The reset trigger is any two-syllable command such as “Reset”. Any type of momentary measurement device may be controlled in this way, including time interval measurements, event counting, length measuring, weighing, and electronic metering measurements, and many others.

Abstract: A method includes initiating a call from an interactive voice response (IVR) system to a first device associated with a user in response to a request. The method includes receiving voice input data at the IVR system via the call. The method also includes performing a search of a media content database based at least partially on the voice input data. The method further includes sending search results identifying media content items based on the search of the media content database to a second device associated with the user.