Abstract: A text translation method is described that includes initially acquiring text. Thereafter, first text is determined in the initial text; and second text is determined according to the first text, where the second text is used for describing the first text. Additionally, initial text is translated to obtain initial translation text, and the second text is translated to obtain description translation text. Thereafter, the initial translation text is updated according to the description translation text to obtain target translation text of the initial text.

Abstract: Disclosed are systems and methods including computing-processes executing machine-learning architectures extract vectors representing disparate types of data and output predicted identities of users accessing computing services, without express identity assertions, and across multiple computing services, analyzing data from multiple modalities, for various user devices, and agnostic to architectures hosting the disparate computing service. The system invokes the identification operations of the machine-learning architecture, which extracts biometric embeddings from biometric data and context embeddings representing all or most of the types of metadata features analyzed by the system. The context embeddings help identify a subset of potentially matching identities of possible users, which limits the number of biometric-prints the system compares against an inbound biometric embedding for authentication.

Abstract: A system for controlling unmanned vehicles such as drones, ground vehicles and robots includes multiple human-to-machine interface components to manage interactions efficiently and effectively between humans and robots with respect to control mechanisms (i.e., inputs such as voice-commands or joystick use) and monitoring (i.e., outputs such as camera or other sensor feeds, geolocation overlay, or audio feedbacks). A system according to the principles of the invention includes numerous modalities for control (e.g., voice-control, gesture-control, touch screen, joystick or other hand-held controllers) as well as monitoring (visual screen display, heads-up-display, audio feedbacks, geolocation overlay, haptic feedback, wearable sensor devices). The system is preferably expandable and may include additional modalities in the future, such as eye-tracking as compared to voice or gesture control.

Abstract: A method for processing sound that includes, generating one or more noise component estimates relating to an electrical representation of the sound and generating an associated confidence measure for the one or more noise component estimates. The method further comprises processing based on the confidence measure, the sound.

Abstract: A method of generating content in association with an information search and retrieval system. It begins by receiving a query from a user. The query is semantically-searched to identify a context. A conversation history between the user and the system is identified. An enriched query is then generated by associating to the query both the context and at least a portion of the conversation history. The enriched query is then evaluated/processed by a generative-AI. In response, information associated with the enriched query is received from the generative-AI. A response to the query is then generated using the information, e.g., by passing the information back to the user, by modifying (e.g., editing or supplementing) the information to generate modified information and passing the modified information back to the user, or by dismissing the information. If sensitive information is identified in the utterance, it is masked prior to generating the enriched query.

Abstract: Deep learning techniques are disclosed for extraction of embedded data from documents. In an exemplary technique, a set of unstructured text data is received. One or more text groupings are generated by processing the set of unstructured text data. One or more text grouping embeddings are generated in a format for input to a machine learning model based on the one or more generated text groupings. One or more output predictions are generated by inputting the one or more text grouping embeddings into the machine learning model. Each output prediction of the one or more output predictions correspond to a predicted aspect of a text grouping of the one or more text groupings.

Abstract: A method of assisting a user. The method including obtaining a plurality of rules having condition components and action components, the action components specifying conversation schemas, detecting, by a sensor, a fact related to an environment of the user, identifying a rule, of the plurality of rules, having a condition component that is satisfied by the detected fact, initiating a conversation with the user according to a conversation schema of the action component of the rule of the plurality of rules, and performing an action in response to a positive statement by the user.

Abstract: The present disclosure provides a question answering method and apparatus for query information. The method may include: receiving query information input by a user, and analyzing a query target comprised in the query information; recalling candidate answers from a pre-generated knowledge graph based on the query target, where the knowledge graph is constructed based on inherent data in a map database and dynamic data of historical users, and the dynamic data includes at least one of comment data, search data, or spatiotemporal big data; and returning, in response to that there is a target answer whose matching degree with the query target exceeds a preset threshold in the candidate answers, the target answer to the user.

Abstract: Software programming provides multi-lingual capabilities for typewritten characters. An information handling system may be programmed to identify any language-specific character typed in any human, natural language. The information handling system presents a menu of supported languages, and a user may select her desired language of use. As the user then types on a keyboard, the information handling system receives scancodes. The information handling system accesses a comprehensive, universal database storing language-specific characters used in many languages. The information handling system uses the database to identify which key, and thus which language-specific character, was depressed, according to the user's desired language of use. Should the information handling system be shared by multiple users, any of the users may switch the language of use and type using the corresponding language-specific characters.

Abstract: An acoustic control apparatus includes a processor with hardware. The processor calculates a first relational expression between acoustic filter coefficients of acoustic filters to be applied to voice signals containing information of sounds played back by two or more sound sources, based on an amplification magnification in a sound amplification control point with respect to the sounds played back by the two or more sound sources, and on transfer functions between the sound amplification control point and the two or more sound sources. The processor calculates a second relational expression between the acoustic filter coefficients, based on information of a frequency of the voice signals, and on an interval between the two or more sound sources. The processor calculates the acoustic filter coefficients based on the first relational expression and the second relational expression.

Abstract: The present disclosure provides methods and apparatuses for phrase-based end-to-end text-to-speech (TTS) synthesis. A text may be obtained. A target phrase in the text may be identified. A phrase context of the target phrase may be determined. An acoustic feature corresponding to the target phrase may be generated based at least on the target phrase and the phrase context. A speech waveform corresponding to the target phrase may be generated based on the acoustic feature.

Abstract: Systems and methods for caching on-device commands utilizing utterance patterns are disclosed. For example, user utterances and resulting selected commands are analyzed to determine which utterances result in consistently-selected commands. Pattern data is generated indicating an association between these utterances and commands. The pattern data is stored in an on-device storage and utilized to select a command to be performed when the associated utterances are identified from audio data. When new features are developed for cloud-side services, a determination is made as to whether commands and utterances associated with the new features are candidates for utterance-to-command patterns, and corresponding pattern data may be sent to the on-device storages.

Abstract: A computational evidence platform extracts clinical concepts from medical evidence sources and creates a database of elemental diagnostic factors and elemental investigations links to medical conditions. Input from a person groups factors and investigations makes corrections and adds a ranking Elemental factors and investigations do not include information specific to their associated conditions but include synonyms and a link to a medical ontology. A patient state is determined by extracting patient known diagnostic factors and investigation results from the patient chart. These known factors and results are matched to the database and a ranking of likely conditions are output. Next-best actions per condition are output by determining factors not yet known and investigations not yet performed. Next-best actions across conditions are determined by performing a recursive tree search of the database and assuming that unknown factors are now known to generate a score for each assumption.

Abstract: Provided is an information processing system including: a voice information acquisition unit that acquires voice information including an utterance made by a person; a status acquisition unit that acquires status information related to status of the person; and a support information generation unit that generates support information used for supporting operation of the person based on the voice information and the status information.

Abstract: This relates to intelligent automated assistants and, more specifically, to intelligent context sharing and task performance among a collection of devices with intelligent automated assistant capabilities. An example method includes, at a first electronic device participating in a context-sharing group associated with a first location: receiving a user voice input; receiving, from a context collector, an aggregate context of the context-sharing group; providing at least a portion of the aggregate context and data corresponding to the user voice input to a remote device; receiving, from the remote device, a command to perform one or more tasks and a device identifier corresponding to a second electronic device; and transmitting the command to the second electronic device based on the device identifier, wherein the command causes the second electronic device to perform the one or more tasks.

Abstract: A voice-based word recognition device, system, and methods are provided for detecting and selectively modifying offensive words. The voice-based word recognition system may be used to monitor and receive signal data from an input/output source. The system may include a voice-based word detector configured to identify a potentially offensive word or phrase from the received signal data. The system may be implemented to analyze whether the identified potentially offensive word or phrase matches an offensive word or phrase from a list of predetermined words. The system may then generate alert data in response to the identified potentially offensive word or phrase matching the offensive word or phrase. As such, the system may therefore modify the matched offensive word or phrase in response to the generated alert data, such that the matched offensive word or phrase is thereby modified prior to audio output data being generated and transmitted to external users.

Abstract: Provided is an information processing system including: a voice information acquisition unit that acquires voice information including an utterance made by a person; a status acquisition unit that acquires status information related to status of the person; and a support information generation unit that generates support information used for supporting operation of the person based on the voice information and the status information.

Abstract: Systems and methods disclosed herein include (i) receiving a voice command via at least one microphone of a networked microphone device, wherein the networked microphone device is configured to receive voice commands for a media playback system, and wherein the media playback system comprises the networked microphone device and a first playback device configured to play back content, (ii) determining that the networked microphone device is not configured to play back the content, (iii) in response to determining that the networked microphone is not configured to play back the content, determining that the first playback device is available to play back the content, (iv) causing the first playback device to play back the content, (v) determining that the first playback device is no longer available to play back the content, and (vi) selecting a second playback device to play back the content.

Abstract: Provided is an information processing system including: a voice information acquisition unit that acquires voice information including an utterance made by a person; a status acquisition unit that acquires status information related to status of the person; and a support information generation unit that generates support information used for supporting operation of the person based on the voice information and the status information.

Abstract: A system and method that overcomes technological hurdles related to litigation-related management is disclosed. The technological hurdles were overcome with industry-transformative innovations in in-person, hybrid, and remote legal proceedings; court reporting; testimony management; trial preparation; and utilization of video evidence, to name several. These innovations resulted in many advantages, such as could-based testimony management, scalable digital transformation, dramatic savings in litigation costs, and fast turn-around on certified transcripts, to name several.