Abstract: A recognition dictionary creation device identifies the language of a reading of an inputted text which is a target to be registered and adds a reading with phonemes in the language identified thereby to the target text to be registered, and also converts the reading of the target text to be registered from the phonemes in the language identified thereby to phonemes in a language to be recognized which is handled in voice recognition to create a recognition dictionary in which the converted reading of the target text to be registered is registered.

Abstract: Appropriate processing results or appropriate apparatuses can be selected with a control device that selects the most probable speech recognition result by using speech recognition scores received with speech recognition results from two or more speech recognition apparatuses; sends the selected speech recognition result to two or more translation apparatuses respectively; selects the most probable translation result by using translation scores received with translation results from the two or more translation apparatuses; sends the selected translation result to two or more speech synthesis apparatuses respectively; receives a speech synthesis processing result including a speech synthesis result and a speech synthesis score from each of the two or more speech synthesis apparatuses; selects the most probable speech synthesis result by using the scores; and sends the selected speech synthesis result to a second terminal apparatus.

Abstract: Systems and methods for suggesting a pause position within electronic text are disclosed herein. According to an aspect, a method may include receiving identification of a current user position within electronic text residing on an electronic device. For example, a current user position may be a page of an e-book that is currently being displayed to a reader or user. The method may include determining a suggested pause position within the electronic text based on the current user position. For example, the suggested pause position may be determined based on the reader's profile, a reading behavior of other readers, metadata, or combinations thereof. The method may also include presenting the suggested pause position on a user interface of the electronic device.

Abstract: In conventional network-type speech translation systems, devices or models for recognizing or synthesizing speech cannot be changed in accordance with speakers' attributes, and therefore, accuracy is reduced or inappropriate output occurs in each process of speech recognition, translation, and speech synthesis. Accuracy of each processing of speech translation, translation, or speech synthesis is improved and appropriate output is performed in a network-type speech translation system by, based on speaker attributes, appropriately changing the server to perform speech recognition or the speech recognition model, appropriately changing the translation server to perform translation or the translation model, or appropriately changing the speech synthesis server or speech synthesis model.

Abstract: In one embodiment, a method provides for monitoring and analyzing communications of a monitored user on behalf of a monitoring user, to determine whether the communication includes a violation. For example, SMS messages, MMS messages, IMs, e-mails, social network site postings or voice mails of a child may be monitored on behalf of a parent. In one embodiment, an algorithm is used to analyze a normalized version of the communication, which algorithm is retrained using results of past analysis, to determine a probability of a communication including a violation.

Abstract: A method and mobile device for awareness of language ability are provided. “Repeated pattern index”-related properties, such as, a vocabulary usage amount, a vocabulary type, or a ratio, a time point, a time length or repeated contents of a repeated voice segment, and “community interaction index”-related properties, such as, a number of persons who speak with a user, a conversation time length, or whether the user talks alone during each time interval, are extracted according to voice data collected by a voice collection element worn on the user. Then, a language ability of the user is further calculated, so as to provide evaluation of the language ability of a dementia patient for reference.

Abstract: Herein disclosed is a gaming machine executing a game and paying out a predetermined amount of credits according to a game result; generating voice data based on a player's voice; identifying a voice pattern corresponding to the voice data by retrieving the dialogue voice database and identifying a type of voice corresponding to the voice data, so as to store the voice data along with the voice pattern into the memory; calculating a value indicative of a game result, and updating the play history data stored in the memory using the result of the calculation; comparing the play history data thus updated with a predetermined threshold value data; generating voice data according to the voice pattern based on the play history data if the play history data thus updated exceeds the predetermined threshold value data; and outputting voices from the speaker.

Abstract: A system and method for generating word alignments from pairs of aligned text strings are provided. A corpus of text strings provides pairs of text strings, primarily sentences, in source and target languages. A first alignment between a text string pair creates links therebetween. Each link links a single token of the first text string to a single token of the second text string. A second alignment also creates links between the text string pair. In some cases, these links may correspond to bi-phrases. A modified first alignment is generated by selectively modifying links in the first alignment which include a word which is infrequent in the corpus, based on links generated in the second alignment. This results in removing at least some of the links for the infrequent words, allowing more compact and better quality bi-phrases, with higher vocabulary coverage, to be extracted for use in a machine translation system.

Abstract: A joint optimization strategy is employed for combining translation hypotheses from multiple machine-translation systems. Decisions on word alignment, between the hypotheses, ordering, and selection of a combined translation output are made jointly in accordance with a set of features. Additional features that model alignment and ordering behavior are also provided and utilized.

Abstract: A system and a method for phrase-based translation are disclosed. The method includes receiving source language text to be translated into target language text. One or more dynamic bi-phrases are generated, based on the source text and the application of one or more rules, which may be based on user descriptions. A dynamic feature value is associated with each of the dynamic bi-phrases. For a sentence of the source text, static bi-phrases are retrieved from a bi-phrase table, each of the static bi-phrases being associated with one or more values of static features. Any of the dynamic bi-phrases which each cover at least one word of the source text are also retrieved, which together form a set of active bi-phrases. Translation hypotheses are generated using active bi-phrases from the set and scored with a translation scoring model which takes into account the static and dynamic feature values of the bi-phrases used in the respective hypothesis. A translation, based on the hypothesis scores, is then output.

Abstract: A system and method implements a command system in a speech recognition context in such a way as to enable a user to speak a voice command in a first spoken language to a computer that is operating an application in a second spoken language configuration. The command system identifies the first spoken language the user is speaking, recognizes the voice command, identifies the second spoken language of a target application, and selects the command action in the second spoken language that correlates to the voice command provided in the first spoken language.

Abstract: A method of and system for managing nametags including receiving a command from a user to store a nametag, prompting the user to input a number to be stored in association with the nametag, receiving an input for the number from the user, prompting the user to input the nametag to be stored in association with the number, receiving an input for the nametag from the user, processing the nametag input, and calculating confusability of the nametag input in multiple individual domains including a nametag domain, a number domain, and a command domain.

Abstract: A method and system comprising an automated analysis of at least one corpus of natural language text is disclosed. For each sentence of a corpus, the analysis 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 generated syntactic and semantic 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 as disclosed herein includes at least one automatic preliminary analyzed corpus of sentences comprising searched values of linguistic, syntactic and semantic parameters.

Abstract: Disclosed are systems, methods and computer-readable media for using a local communication network to generate a speech model. The method includes retrieving for an individual a list of numbers in a calling history, identifying a local neighborhood associated with each number in the calling history, truncating the local neighborhood associated with each number based on the at least one parameter, retrieving a local communication network associated with each number in the calling history and each phone number in the local neighborhood, and creating a language model for the individual based on the retrieved local communication network. The generated language model may be used for improved automatic speech recognition for audible searches as well as other modules in a spoken dialog system.

Abstract: A method for recognizing speech involves presenting an utterance to a speech recognition system and determining, via the speech recognition system, that the utterance contains a particular expression, where the particular expression is capable of being associated with at least two different meanings. The method further involves splitting the utterance into a plurality of speech frames, where each frame is assigned a predetermined time segment and a frame number, and indexing the utterance to i) a predetermined frame number, or ii) a predetermined time segment. The indexing of the utterance identifies that one of the frames includes the particular expression. Then the frame including the particular expression is re-presented to the speech recognition system to verify that the particular expression was actually recited in the utterance.

Abstract: A computer-implemented speech recognition system described herein includes a receiver component that receives a plurality of detected units of an audio signal, wherein the audio signal comprises a speech utterance of an individual. A selector component selects a subset of the plurality of detected units that correspond to a particular time-span. A generator component generates at least one feature with respect to the particular time-span, wherein the at least one feature is one of an existence feature, an expectation feature, or an edit distance feature. Additionally, a statistical speech recognition model outputs at least one word that corresponds to the particular time-span based at least in part upon the at least one feature generated by the feature generator component.

Abstract: Ambiguities in a natural language expression are interpreted by jointly disambiguating multiple alternative syntactic and semantic interpretations. More than one syntactic alternative, represented by parse contexts, are analyzed together with joint analysis of referents, word senses, relation types, and layout of a semantic representation for each syntactic alternative. Best combinations of interpretations are selected from all participating parse contexts, and are used to form parse contexts for the next step in parsing.

Abstract: An emotive advisory system for use by one or more occupants of an automotive vehicle includes a directional speaker array, and a computer. The computer is configured to determine an audio direction, and output data representing an avatar for visual display. The computer is further configured to output data representing a spoken statement for the avatar for audio play from the speaker array such that the audio from the speaker array is directed in the determined audio direction. A visual appearance of the avatar and the spoken statement for the avatar convey a simulated emotional state.

Abstract: A mechanism for local language numeral conversion in dynamic numeric computing is disclosed. A method of embodiments of the invention includes receiving a string array of numeric data in a local language, wherein the numeric data used in dynamic calculations performed by the application, converting characters of the string array of numeric data from local language characters to corresponding English digits in an American Standard Code for Information Interchange (ASCII) format by utilizing a number conversion matrix, and providing the English digits in the ASCII format to a processing function of the application for use with the dynamic calculations of the application.

Abstract: Mechanisms are provided to facilitate communications across language boundaries. In particular, translation solutions are described which automatically determine communication preferences of various participants in a communication session and further translate user inputs received during the communication session so as to confirm with communication preferences of the participants that receive the user input.

Abstract: The present invention is an Advanced Natural Language Translation System (ANLTS). It discloses a method to address the most common variation in the world, which is communication gap between people of different ethnicity. Typically, communication is said to be successful between two people if someone speaks and opponent party can understand. In other words the intended recipient's brain language area can comprehend the speech. The problem of not understanding the speech of others is the cause of language barriers. So, this invention discloses a method to solve the language barrier problem where it is capable of interpreting meaning of speech in one language to a language native to another—basically to a language the recipient brain can comprehend. Imagine a world where we can communicate with our native language to everyone without the need of human translators, interpreters, hand-held device and language translation books.

Abstract: An apparatus is provided that includes a processor and a memory. The processor is configured to determine a category for a group of isolated noun phrases in a structured or semi-structured data source stored in the memory. The group of isolated noun phrases includes one or more isolated noun phrases. The processor is also configured to translate the group of isolated noun phrases from a source language to a target language using a category-driven isolated noun phrase translation. The determination of the category and the category-driven isolated noun phrase translation are performed based on context derived from the group of isolated noun phrases.

Abstract: A language identification system that includes a universal phoneme decoder (UPD) is described. The UPD contains a universal phoneme set representing both 1) all phonemes occurring in the set of two or more spoken languages, and 2) captures phoneme correspondences across languages, such that a set of unique phoneme patterns and probabilities are calculated in order to identify a most likely phoneme occurring each time in the audio files in the set of two or more potential languages in which the UPD was trained on. Each statistical language models (SLM) uses the set of unique phoneme patterns created for each language in the set to distinguish between spoken human languages in the set of languages. The run-time language identifier module identifies a particular human language being spoken by utilizing the linguistic probabilities supplied by the one or more SLMs that are based on the set of unique phoneme patterns created for each language.

Abstract: A speech recognition apparatus and method that can improve speech recognition rate and recognition speed by reflecting information for dynamic display, are provided. The speech recognition apparatus generates a display variation signal indicating that variations have occurred on a screen and creates display information about the varied screen. The speech recognition apparatus adjusts a word weight for at least one word related to the varied screen and a domain weight for at least one domain included in the varied screen, according to the display variation signal and the display information. The adjusted word weight and the adjusted domain weight are dynamically reflected in a language model that is used for speech recognition.

Abstract: A document containing text in a source language may be translated into a target language based on content associated with that document, in conjunction with the present technology. An indication to perform an optimal translation of a document into a target language may be received via a user interface. The document may then be accessed by a computing device. The optimal translation is executed by a preferred translation engine of a plurality of available translation engines. The preferred translation engine is the most likely to produce the most accurate translation of the document among the plurality of available translation engines. Additionally, the preferred translation engine may be identified based on content associated with the document. The document is translated into the target language using the preferred translation engine to obtain a translated document, which may then be outputted by a computing device.

Abstract: A message occurrence can be detected when a software application runs on a computing device. The message occurrence can be an occurrence where a text containing message is presented upon a user interface of the software application or a log associated with the software application is updated with a text containing message. A user context for the message occurrence can be determined. The user context can include a user sequence and an execution path. Message occurrence information can be conveyed to a message context catalog. Within the message context catalog, the message occurrence information can be indexed against unique message identifiers. Message occurrence information from the message context catalog can be presented in a computer's user interface when a message uniquely identified by the message identifier is presented in the user interface. The user interface can permit a user to edit text of messages.

Abstract: The invention has as its objective to aid an individual proficient in a first language in learning the pronunciation and spelling of a second language. To achieve this objective, a language teaching device comprises a processor, a memory, a presentation screen, an audio component and an input unit. The memory has a database, audio files and games. The database is structured to have at least three subsets. The first subset lists spelling patterns in the first and second languages which have similar pronunciations and words in the second language which exemplify the pronunciation. A second subset lists spelling patterns and words in the second language exemplifying a pronunciation not found in the first language, the listed spelling patterns and associated pronunciation in the second subset follow a general rule of pronunciation in the second language.

Abstract: Methods, systems, and apparatus, including computer program products, for detecting writing systems and languages are disclosed. In one implementation, a method is provided. The method includes receiving text; detecting a first segment of the text, where a substantial amount of the first segment represents a first language; detecting a second segment of the text, where a substantial amount of the second segment represents a second language; identifying scores for each n-gram of size x included in the text; and detecting an edge that identifies a transition from the first language to the second language in the text based on variations of the scores.

Abstract: A mining system applies queries to retrieve result items from an unstructured resource. The unstructured resource may correspond to a repository of network-accessible resource items. The result items that are retrieved may correspond to text segments (e.g., sentence fragments) associated with resource items. The mining system produces a structured training set by filtering the result items and establishing respective pairs of result items. A training system can use the training set to produce a statistical translation model. The translation model can be used in a monolingual context to translate between semantically-related phrases in a single language. The translation model can also be used in a bilingual context to translate between phrases expressed in two respective languages. Various applications of the translation model are also described.

Abstract: A system and method for porting of existing speech recognition solutions in a source language to a target language has been disclosed. The system envisaged by the present invention enables porting of a working speech recognition solution in the source language to a working system in the target language, thus minimising the development process and reusing existing speech recognition solution components to recognise multiple languages.

Abstract: This invention relates to a dialog design apparatus and method. More specifically, this invention relates to a state oriented dialog design apparatus and method to facilitate the creation of natural language dialogs and creating data structures for voice user interfaces. The dialog design apparatus may include inputting means for receiving a user's prompt; response generating means for the user to generating at least one response; dialog structure generating means for structurally managing the user's input and response; and output means for outputting and displaying at least one dialog structure. A state in the present invention may include at least one system prompt and at least one response, and a linking unit may link a first state to a second state related to the first state, link the second state to a third state, and so on until certain system actions are achieved. A loop detecting unit in the present invention detects and identifies loops in the dialog structure.

Abstract: A computer-implemented system and a method for pruning a library of bi-phrases, suitable for use in a machine translation system are provided. The method includes partitioning a bi-phrase library into a set of sub-libraries. The sub-libraries may be of different complexity such that, when pruning bi-phrases from the plurality of sub-libraries is based on a common noise threshold, a complexity of bi-phrases is taken into account in pruning the bi-phrases.

Abstract: A problem to be solved is to robustly detect a pronunciation variation example and acquire a pronunciation variation rule having a high generalization property, with less effort. The problem can be solved by a pronunciation variation rule extraction apparatus including a speech data storage unit, a base form pronunciation storage unit, a sub word language model generation unit, a speech recognition unit, and a difference extraction unit. The speech data storage unit stores speech data. The base form pronunciation storage unit stores base form pronunciation data representing base form pronunciation of the speech data. The sub word language model generation unit generates a sub word language model from the base form pronunciation data. The speech recognition unit recognizes the speech data by using the sub word language model.

Abstract: A phrase-based translation system and method includes a statistically integrated phrase lattice (SIPL) (H) which represents an entire translational model. An input (I) is translated by determining a best path through an entire lattice (S) by performing an efficient composition operation between the input and the SIPL. The efficient composition operation is performed by a multiple level search where each operand in the efficient composition operation represents a different search level.

Abstract: Embodiments of a dialog system that utilizes a multi-modal input interface for recognizing user input in human-machine interaction (HMI) systems are described. Embodiments include a component that receives user input from a plurality of different user input mechanisms (multi-modal input) and performs certain synchronization and disambiguation processes. The multi-modal input components synchronizes and integrates the information obtained from different modalities, disambiguates the input, and recovers from any errors that might be produced with respect to any of the user inputs. Such a system effectively addresses any ambiguity associated with the user input and corrects for errors in the human-machine interaction.

Abstract: A system for directing media streams during a conference call, including an enterprise, at least one network provided within the enterprise and in communication with a plurality of communication devices, a platform provided within the enterprise and in communication with the network, the platform comprising a protocol layer, a services layer and an application layer, and a conference call server in communication with the platform, wherein the platform is configured for receiving media streams from each of the communication devices and instructing the conference call server on how to direct the media streams to and from each of the communication devices.

Abstract: In a verification support apparatus, a content analysis section analyzes a content to divide the content into paragraphs, extract region/culture-specific data, and store the analysis results in an analysis result storage section. A first verification section verifies, based on the analysis results, the consistency between the content and locale of a paragraph and the consistency between the paragraph and locale of the region/culture-specific data. A second verification section verifies, based on the analysis results, the correspondence between a paragraph of language A and a paragraph of language B and the consistency between the region/culture-specific data of language A and the region/culture-specific data of language B. A content update section updates the content so that the results of verification by the first verification section or the second verification section can be displayed in a way a person in charge of verification can easily understand.

Abstract: Systems and methods for receiving natural language queries and/or commands and execute the queries and/or commands. The systems and methods overcome the deficiencies of prior art speech query and response systems through the application of a complete speech-based information query, retrieval, presentation and command environment. This environment makes significant use of context, prior information, domain knowledge, and user specific profile data to achieve a natural environment for one or more users making queries or commands in multiple domains. Through this integrated approach, a complete speech-based natural language query and response environment can be created. The systems and methods creates, stores and uses extensive personal profile information for each user, thereby improving the reliability of determining the context and presenting the expected results for a particular question or command.

Abstract: A system and method for hybrid machine translation approach is based on a statistical transfer approach using statistical and linguistic features. The system and method may be used to translate from one language into another. The system may include at least one database, a rule based translation module, a statistical translation module and a hybrid machine translation engine. The database(s) store source and target text and rule based language models and statistical language models. The rule based translation module translates source text based on the rule based language models. The statistical translation module translates source text based on the statistical language models. A hybrid machine translation engine, having a maximum entropy algorithm, is coupled to the rule based translation module and the statistical translation module and is capable of translating source text into target text based on the rule based and statistical language models.

Abstract: Embodiments may be a standalone module or part of mobile devices, desktop computers, servers, stereo systems, or any other systems that might benefit from condensed audio presentations of item structures such as lists or tables. Embodiments may comprise logic such as hardware and/or code to adjust the temporal characteristics of items comprising words. The items maybe included in a structure such as a text listing or table, an audio listing or table, or a combination thereof, or may be individual words or phrases. For instance, embodiments may comprise a keyword extractor to extract keywords from the items and an abbreviations generator to generate abbreviations based upon the keywords. Further embodiments may comprise a text-to-speech generator to generate audible items based upon the abbreviations to render to a user while traversing the item structure.

Abstract: Methods and technologies providing translations of web queries based on an analysis of user behavior in click-through data. These methods and technologies generates large-scale and timely query translation pairs guided by a small set of seed word pairs from a dictionary, without relying on additional knowledge or complex models.

Abstract: Multi-mode commissioning/decommissioning of a wireless monitoring device (Tag) for managing assets and shipments is disclosed. Users can request commissioning, status resets and decommissioning of Tags using multiple modes of communication. The users are authenticated by an information service that receives the requests. Responsive to a successful authentication of a user, the information service receives a tag identifier and an asset identifier from the user. A tracking application associates the Tag identifier and the asset identifier. After the Tag is associated with the asset, the tracking application can successfully track the geographic location and status data of the asset from the Tag. The location data can be used by the tracking application to track assets in real-time. The status data and location data can be used by the tracking application to detect and verify tamper conditions, including tamper alerts triggered by geo-fences, authorized inspection of the asset, and environmental exceptions.

Abstract: A post-editing apparatus for correcting translation errors, includes: a translation error search unit for estimating translation errors using an error-specific language model suitable for a type of error desired to be estimated from translation result obtained using a translation system, and determining an order of correction of the translation errors; and a corrected word candidate generator for sequentially generating error-corrected word candidates for respective estimated translation errors on a basis of analysis of an original text of the translation system. The post-editing apparatus further includes a corrected word selector for selecting a final corrected word from among the error-corrected word candidates by using the error-specific language model suitable for the type of error desired to be corrected, and incorporating the final corrected word in the translation result, thus correcting the translation errors.

Abstract: An information retrieval translation apparatus for translating a plurality of Chinese terms including a first Chinese term and a second Chinese term is disclosed. The information retrieval oriented translation apparatus includes a first language database, a second language database, a comparison module and a translation term acquisition module. The first language database stores a plurality of first indices and a plurality of corresponding first translation terms. The second language database stores a plurality of second indices and a plurality of corresponding second translation terms. The comparison module compares the first and second Chinese terms with the first and second indices, respectively. The translation term acquisition module acquires the corresponding first translation term for the first index which corresponds to the first Chinese term, and the corresponding second translation term for the second index which corresponds to the second Chinese term.

Abstract: A computer implemented method, apparatus, and computer program product for generating audio cohorts. An audio analysis engine receives audio data from a set of audio input devices. The audio data is associated with a plurality of objects. The audio data comprises a set of audio patterns. The audio data is processed to identify attributes of the audio data to form digital audio data. The digital audio data comprises metadata describing the attributes of the audio data. A set of audio cohorts is generated using the digital audio data and cohort criteria. Each audio cohort in the set of audio cohorts comprises a set of objects from the plurality of objects that share at least one audio attribute in common.

Abstract: Embodiments of a dialog system that utilizes contextual information to perform recognition of proper names are described. Unlike present name recognition methods on large name lists that generally focus strictly on the static aspect of the names, embodiments of the present system take into account of the temporal, recency and context effect when names are used, and formulates new questions to further constrain the search space or grammar for recognition of the past and current utterances.

Abstract: An Integrated Phonetic Chinese System includes a module of Chinese pronunciation keys, a module of Romanized Chinese scripts, a module of input method that allows users to input Chinese characters and pronunciation keys and Romanized scripts and a module of advanced input method utilizing a 24 key position matrix that allows users to input Chinese characters and pronunciation keys and Romanized script with maximum speed and efficiency.

Abstract: Disclosed are methods and apparatus for supporting multi-lingual maps are disclosed. In one embodiment, a query indicating that a map is requested is received. A language in which the map is to be presented is determined. A set of map data for rendering the map is obtained, wherein the set of map data includes image data and text data. A translation of the text data in the set of map data is obtained such that the text data is translated to the language in which the map is to be presented. The image data and the translated text data are then provided.

Abstract: A transformation can be derived which would represent that processing required to convert a male speech model to a female speech model. That transformation is subjected to a predetermined modification, and the modified transformation is applied to a female speech model to produce a synthetic children's speech model. The male and female models can be expressed in terms of a vector representing key values defining each speech model and the derived transformation can be in the form of a matrix that would transform the vector of the male model to the vector of the female model. The modification to the derived matrix comprises applying an exponential p which has a value greater than zero and less than 1.

Abstract: The phonetic natural language translation system receives audio output from an electro acoustic device connected as a component in an audio system presented in a theater or auditorium, to identify any speech signal contained within the audio output. The speech signals are broken down into recognizable phonemes. The sequentially generated phonemes are then regrouped to form recognizable words in one of the 6,700 languages spoken around the world. Sentences are then formed using the grammatical rules of the recognized language so that each sentence translated into each of the audience's preferred language without any external translators. The preferred language of each audience is identified during ticket booking; an algorithm stores the audience seat number along with preferred language. The translated audio signals are distributed to an each seat's armrest such that each viewer listens and understands the foreign language audible program or speech in their own preferred language.