Abstract: A method for remote communication based on a real-time translation service according to an embodiment of the present disclosure, as a method for providing remote communication based on a real-time translation service by a real-time translation application executed by at least one or more processors of a computing device, comprises performing augmented reality-based remote communication; setting an initial value of a translation function for the remote communication; obtaining communication data of other users through the remote communication; performing language detection for the obtained communication data; when a target translation language is detected within the communication data from the performed language detection, translating communication data of the target translation language detected; and providing the translated communication data.

Abstract: A method for natural language, includes: determining a slot tagging result output by a Bi-directional Long Short-Term Memory-Conditional Random Field algorithm (BiLSTM-CRF) model after slot tagging on conversation data input by a user; determining reward information based on the slot tagging result and a reward of the user for the slot tagging result; and performing reinforcement learning on the BiLSTM-CRF model according to the reward information.

Abstract: Techniques for improving a semantic parser of a dialog system, by breaking the semantic parser into a coarse semantic parser and a fine semantic parser, are described. A method described herein includes accessing an utterance received in a dialog system. The utterance is a text-based natural language expression. The method further includes applying a coarse semantic parser to the utterance to determine an intermediate logical form for the utterance. The intermediate logical form indicates one or more intents in the utterance. The method further includes applying a fine semantic parser to the intermediate logical form to determine a logical form for the utterance. The logical form is a syntactic expression of the utterance according to an established grammar, and the logical form includes one or more parameters of the one or more intents. The logical form can be used to conduct a dialog with a user of the dialog system.

Abstract: A semantic processing method includes the following steps of: segmenting an input sentence into a plurality of lexicons according to a lexicon database, wherein the lexicon table includes a plurality of table blocks, and the table blocks are respectively located at a plurality of levels of the lexicon table; referring one part of speech or a plurality of parts of speech, corresponding to one of the lexicons of the table blocks, in the lexicon database; performing at least one grammar rule for each of the table blocks of the levels according to the part of speech, the plurality of parts of speech, the part of speech sequence or the plurality of part of speech sequences corresponding to the table blocks of the lexicon table; and outputting a parse tree according to the table blocks in the lexicon table that conform to the at least one grammar rule.

Abstract: The present disclosure provides method and apparatus for processing a message. A statement sentence message and a message processing parameter associated with a user's session message are obtained. One or more first statement sentence nodes that are semantic-matched with the statement sentence message are determined in the knowledge map. One or more second statement sentence nodes corresponding to the message processing parameters are obtained from the knowledge map, based on the node relationship properties of the first statement sentence nodes. A response is generated based at least in part on statement sentences of the one or more second statement sentence nodes. The generated response is provided to the user.

Abstract: Disclosed herein are systems, computer-implemented methods, and computer-readable media for dialog modeling. The method includes receiving spoken dialogs annotated to indicate dialog acts and task/subtask information, parsing the spoken dialogs with a hierarchical, parse-based dialog model which operates incrementally from left to right and which only analyzes a preceding dialog context to generate parsed spoken dialogs, and constructing a functional task structure of the parsed spoken dialogs. The method can further either interpret user utterances with the functional task structure of the parsed spoken dialogs or plan system responses to user utterances with the functional task structure of the parsed spoken dialogs. The parse-based dialog model can be a shift-reduce model, a start-complete model, or a connection path model.

Abstract: Techniques for speech-to-text hypothesis generation and hypothesis selection described. A text input representing at least part of a voice recording is received from a speech-to-text component. A first text alternative is generated using a finite state transducer based at least in part on the text input. A hypothesis from a hypothesis set is selected using a language model that includes probabilities for sequences of words, the hypothesis set including the text input and the first text alternative. A selected hypothesis text associated with the selected hypothesis is sent to a search engine.

Abstract: Devices, systems, and methods are provided for classifying voice search queries. A system may receive voice data associated with a voice utterance, the system being associated with a network. The system may determine that the voice data is associated with a question, and may determine an absence of an answer to the question. The system may determine a score associated with the question, the score indicative of a risk of disclosure of sensitive information associated with a person. The system may determine that the score fails to satisfy a threshold, and may send the question to a device, wherein the device is remote from the network. The system may receive data associated with the question.

Abstract: Techniques are described that enable a user to edit and customize captions generated by a social networking system, such as transcriptions of an audio clip. In some cases, a social networking system receives, from a first user account, a video and an audio clip associated with the video, and determines that the audio clip contains speech. The social networking system may leverage a speech-to-text component to generate a first text caption based at least in part on the speech in the audio clip. The social networking system provides the first text caption to the first user account, and receives a user input to modify a word included in the first text caption. The social networking system generates a second text caption based at least in part on the user input, and provides the video, including the second text caption, to a second user account.

Abstract: In one aspect, a computerized method useful for implementing a language neutral virtual assistant including the step of providing a language detector. The language detector comprises one or more trained language classifiers. With language detector identifying a language of an incoming message from a user to an artificially intelligent (AI) personal assistant. The method includes the step of receiving an incoming message to the AI personal assistant. The method includes the step of normalizing the incoming message, wherein the normalizing the incoming message comprises a set of spelling corrections and a set of grammar corrections. The method includes the step of translating the incoming message to a specified language with a specified encoding process and a specified decoding process. The method includes the step of providing an AI personal assistant engine that comprise an artificial intelligence which conducts a conversation via auditory or textual methods.

Abstract: Systems described herein may use transformer-based machine classifiers to perform a variety of natural language understanding tasks including, but not limited to sentence classification, named entity recognition, sentence similarity, and question answering. The exceptional performance of transformer-based language models is due to their ability to capture long-term temporal dependencies in input sequences. Machine classifiers may be trained using training data sets for multiple tasks, such as but not limited to sentence classification tasks and sequence labeling tasks. Loss masking may be employed in the machine classifier to jointly train the machine classifier on multiple tasks simultaneously. The user of transformer encoders in the machine classifiers, which treat each output sequence independently of other output sequences, in accordance with aspects of the invention do not require joint labeling to model tasks.

Abstract: Disclosed are a method of encoding a high band of an audio, a method of decoding a high band of an audio, and an encoder and a decoder for performing the methods. The method of decoding a high band of an audio, the method performed by a decoder, includes identifying a parameter extracted through a first neural network, identifying side information extracted through a second neural network, and restoring a high band of an audio by applying the parameter and the side information to a third neural network.

Abstract: The present disclosure discloses a machine learning-based method for defending a voice assistant from being controlled by an inaudible command, including following steps: 1) collecting data of positive and negative samples, 2) performing data segmentation on data of the positive and negative samples; 3) selecting and normalizing sample features; 4) selecting a classifier to be trained and generate a detection model for a malicious voice command; 5) detecting a voice command to be detected by the detection model. The present disclosure selects an original feature selection method, and for smart devices of different types, it is necessary to obtain normal voice commands and malicious voice commands by means of a smart device of this type, and use them as the positive and negative samples to train a specific classifier for the device. Such a customized approach can well solve a problem that detection and defense between devices cannot work.

Abstract: [Problem] Provided is a presentation support system that makes it possible to give effective presentations, for both presentations by machines and normal presenters. [Solution] The presentation support system included: a display unit 3; a material storage unit 5 that stores a presentation material and a plurality of keywords; an audio storage unit 7; an audio analysis unit 9 that analyzes a term contained in a presentation; a keyword order adjustment unit 11 that analyzes an order of appearance of a plurality of keywords contained in the audio analyzed by the audio analysis unit and changes the order of the plurality of keywords on the basis of the order of appearance; and a display control unit 13 that controls content displayed in the display unit 3.

Abstract: An audio source such as a display device configured to present AV content can present the video and send the audio in different languages to the respective devices of different listeners. For example, a device/TV/source can send audio in different languages to connected headphones/smartglasses with speakers/devices/sink. Furthermore, machine learning may be employed both to recognize listeners and correlate them to likely languages and to mimic voices in the played-back audio. Or, the source AV display device may send language in only the selected language of the display device to each listener device, with each receiving listener device converting the audio to the preferred language of the respective listener on the fly.

Abstract: One embodiment provides a method, including: receiving at a digital personal assistant coupled to an information handling device, while receiving a command from a first user, an input from a second user; determining that the input provided by the second user is directed at the first user; providing an indication indicating the command is directed to the digital personal assistant; and ignoring the input provided by the second user. Other aspects are described and claimed.

Abstract: A method includes receiving audio data encoding an utterance and obtaining a set of bias phrases corresponding to a context of the utterance. Each bias phrase includes one or more words. The method also includes processing, using a speech recognition model, acoustic features derived from the audio to generate an output from the speech recognition model. The speech recognition model includes a first encoder configured to receive the acoustic features, a first attention module, a bias encoder configured to receive data indicating the obtained set of bias phrases, a bias encoder, and a decoder configured to determine likelihoods of sequences of speech elements based on output of the first attention module and output of the bias attention module. The method also includes determining a transcript for the utterance based on the likelihoods of sequences of speech elements.

Abstract: Technology is provided for causing a computing system to extract conversation features from a multiparty conversation (e.g., between a coach and mentee), apply the conversation features to a machine learning system to generate conversation analysis indicators, and apply a mapping of conversation analysis indicators to actions and inferences to determine actions to take or inferences to make for the multiparty conversation. In various implementations, the actions and inferences can include determining scores for the multiparty conversation such as a score for progress toward a coaching goal, instant scores for various points throughout the conversation, conversation impact score, ownership scores, etc. These scores can be, e.g., surfaced in various user interfaces along with context and benchmark indicators, used to select resources for the coach or mentee, used to update coach/mentee matchings, used to provide real-time alerts to signify how the conversation is going, etc.

Abstract: Disclosed herein are embodiments of systems, methods, and products comprises an analytic server, which automatically manages appointment scheduling. The analytic server receives a customer request to schedule an appointment. The analytic server determines the required data from both customer and service provider for making the appointment. The analytic server retrieves customer data comprising requested service attributes, user preferences, users attributes from internal database and external data source. The analytic server retrieves service providers' data comprising provider service attributes, providers' attributes from internal database and external data sources. The analytic server accesses external data source by web crawling various websites. The analytic server executes an artificial intelligence model to predict user preferences and needs. The analytic server determines potential service providers best matching the customer's input or predicted preferences.

Abstract: A home appliance including a communication device configured to communicate with another home appliance, a microphone configured to receive a voice from a user, and a processor configured to perform signal processing on first voice data obtained from the microphone and perform voice recognition using the signal-processed first voice data. Wherein the processor generates noise data using second voice data received from the other home appliance and performs the signal processing on the first voice data using the generated noise data.