Abstract: An electronic device and a method for controlling an electronic device are provided. The electronic device according to the disclosure includes a communicator; and a processor configured to: receive information on a plurality of function and a voice command for executing the plurality of functions, and function environment information for executing the plurality of functions, through the communicator, determine whether or not the electronic device executes the plurality of functions based on environment information and the functional environment information of the electronic device, when a received user's voice corresponds to the voice command, and control the electronic device to perform an operation corresponding to the determination result.

Abstract: A system for classifying a language sample intent by receiving a language sample including a set of features, identifying language sample features, determining a tokenization score for the language sample according to the language sample features, eliminating duplicate features according to the tokenization score, determining a term frequency (tf) according to the identified features and the tokenization score, determining an inverse document frequency (idf) according to the identified features and the tokenization score, and generating a term frequency-inverse document frequency (tf-idf) matrix for the identified features.

Abstract: A system and method are provided for analyzing and reacting to interactions between entities using electronic communication channels. The method includes receiving, via the communications module, data captured from a conversational exchange between a first entity communicating with a second entity using an electronic communication channel. The method also includes analyzing the captured data to detect an indication that the first entity is or was distracted during the conversational exchange, is or was disinterested in a portion of the conversational exchange or missed the portion of the conversational exchange. The method also includes determining based on the indication an action to address the distraction during, disinterest in, or missing of, the portion of the conversational exchange; and providing, via the communications module, an automated message to at least one of the first entity and the second entity for executing the action.

Abstract: Automatic extractions of situations includes creating a situation image includes accessing a conversation between a first user and a second user, and generating an abstract knowledge graph at one or more textual levels. The method also includes generating one or more manifests by pruning the abstract knowledge graph and segmenting the pruned abstract knowledge graph. The method further includes converting the one or more manifests into the situation image.

Abstract: The present invention provides an artificial intelligence-based data processing apparatus and method using the same to prevent dispute over various kinds of inconveniences such as inter-floor noise occurring in an apartment house and to solve them in a friendly and communicative manner based on mutual consideration. The AI-based data processing apparatus according to embodiments of the present invention can communicate with neighbors conveniently, quickly and accurately by voice, and communicate in a manner that does not offend each other as if it were through an unbiased mediator. By acting in consideration, it is possible to effectively prevent and resolve inter-floor noise related disputes.

Abstract: An encoder and a method therein for Pyramid Vector Quantizer, PVQ, shape search, the PVQ taking a target vector x as input and deriving a vector y by iteratively adding unit pulses in an inner dimension search loop. The method comprises, before entering a next inner dimension search loop for unit pulse addition, determining, based on the maximum pulse amplitude, maxampy, of a current vector y, whether more than a current bit word length is needed to represent enloopy, in a lossless manner in the upcoming inner dimension loop. The variable enloopy is related to an accumulated energy of the vector y. The performing of this method enables the encoder to keep the complexity of the search at a reasonable level.

Abstract: Systems, methods, and apparatus for using a multimodal response in the dynamic generation of client device output that is tailored to a current modality of a client device is disclosed herein. Multimodal client devices can engage in a variety of interactions across the multimodal spectrum including voice only interactions, voice forward interactions, multimodal interactions, visual forward interactions, visual only interactions etc. A multimodal response can include a core message to be rendered for all interaction types as well as one or more modality dependent components to provide a user with additional information.

Abstract: A method of performing speech recognition, comprises, at a first device: receiving an audio signal representing speech; performing a first data integrity check operation on the received audio signal; performing a speaker recognition process on the received audio signal; forwarding the received audio signal to a second device, wherein the second device comprises a speech recognition function; and forwarding an output of the first data integrity check operation to the second device.

Abstract: Systems and methods of invoking functions of agents via digital assistant applications are provided. Each action-inventory can have an address template for an action by an agent. The address template can include a portion having an input variable used to execute the action. A data processing system can parse an input audio signal from a client device to identify a request and a parameter to be executed by the agent. The data processing system can select an action-inventory for the action corresponding to the request. The data processing system can generate, using the address template, an address. The address can include a substring having the parameter used to control execution of the action. The data processing system can direct an action data structure including the address to the agent to cause the agent to execute the action and to provide output for presentation.

Abstract: A voice analyzer analyzes whether a voice signal input into a voice input unit includes a specific characteristic component. A voice recognizer recognizes a voice represented by the voice signal input into the voice input unit. A response instruction unit instructs a response to a response operation unit that operates in response to the voice recognized by the voice recognizer. A controller controls the voice recognizer not to execute voice recognition processing by the voice recognizer or controls the response instruction unit not to instruct the response operation unit about an instruction content by the voice recognized by the voice recognizer, when the voice analyzer analyzes that the voice signal includes the specific characteristic component.

Abstract: A halftone raster image, suitable for rendering a continuous-tone image, which comprises a plurality of regularly tiled spiral dots. Said spiral dots comprise (i) image pixels arranged as a first arc (200) or as a plurality of arcs which together represent a first spiral (100), and (ii) non-image pixels arranged as a second arc (201) or as a plurality of arcs which together represent a second spiral (101), wherein neighbour halftone dots from said plurality of regularly tiled halftone dots represent a double spiral or triple spiral.

Abstract: Various embodiments generally relate to systems and methods for creation of voice memos while an electronic device is in a driving mode. In some embodiments, a triggering event can be used to indicate that the electronic device is within a car or about to be within a car and that text communications should be translated (e.g., via an application or a conversion platform) into a voice memo that can be played via a speaker. These triggering events can include a manual selection or an automatic selection based on a set of transition criteria (e.g., electronic device moving above a certain speed, following a roadway, approaching a location in a map of a marked car, etc.).

Abstract: Techniques for storing and using multi-session context are described. A system may store context data corresponding to a first interaction, where the context data may include action data, entity data and a profile identifier for a user. Later the stored context data may be retrieved during a second interaction corresponding to the entity of the second interaction. The second interaction may take place at a system different than the first interaction. The system may generate a response during the second interaction using the stored context data of the prior interaction.

Abstract: Described herein is a system for enabling a user to perform complex goals using multiple skills/applications of an intelligent assistant device. Skills may register as consumers of an action or providers of an action, and the consumer skills may be configured to invoke provider skills to perform actions. The system receives a request to perform an action from a skill along with some action data. The system validates the action data, selects another skill to perform the action, and forwards the request to the selected skill to perform the action.

Abstract: A method (100) for generating a domain-specific training set, comprising: generating (130) a generic corpus comprising a plurality of tokenized documents, comprising: (i) parsing (132) a document retrieved from the generic corpus; (ii) preprocessing (134) the parsed document; (iii) tokenizing (136) the preprocessed document; and (iv) storing (138) the tokenized document in the generic corpus; generating (140) an ontology database of tokenized entries, comprising: (i) parsing (142) an ontology entry retrieved from an ontology; (ii) preprocessing (144) the parsed entry; (iii) tokenizing (146) the preprocessed entry; and (iv) storing (148) the tokenized entry in the ontology database; querying (150), using domain-specific tokenized entries from the ontology database, the tokenized documents in the generic corpus; identifying (160), based on the query, a plurality of tokenized documents specific to the domain; and storing (170), in a training set database, the identified tokenized documents as a training set spec

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for language models using domain-specific model components. In some implementations, context data for an utterance is obtained. A domain-specific model component is selected from among multiple domain-specific model components of a language model based on the non-linguistic context of the utterance. A score for a candidate transcription for the utterance is generated using the selected domain-specific model component and a baseline model component of the language model that is domain-independent. A transcription for the utterance is determined using the score the transcription is provided as output of an automated speech recognition system.

Abstract: A method of providing a personalized audio briefing to a user is performed at an electronic device. The device receives identification of information sources associated with the user. Each of the information sources is associated with a content type. The device receives an authorization to access the identified information sources and a preferred order of content types for presentation within the audio briefing. It transmits to a remote system the identification, the authorization, and the preferred order. Following the transmitting, the device receives a verbal input from the user requesting the audio briefing. In response to the verbal input, the device receives a response generated by the remote system, including content from the information sources and information inserted by the remote system based on the authorization to access received from the user. The device outputs an audible response according to the preferred order.

Abstract: Sentiment classification can be implemented by an entity-level multimodal sentiment classification neural network. The neural network can include left, right, and target entity subnetworks. The neural network can further include an image network that generates representation data that is combined and weighted with data output by the left, right, and target entity subnetworks to output a sentiment classification for an entity included in a network post.

Abstract: Devices and techniques are generally described for machine learning personalization as a service for speech processing applications. In various examples, a first request for machine learning prediction for a first speech processing skill. First skill data schema data may be received that describes content of the first speech processing skill. A first machine learning model for the first speech processing skill may be determined. A first feature definition describing a first aspect of the content may be determined. A second feature definition describing user profile data may be determined. A prediction request may be received from the first speech processing skill. First feature data may be generated according to the first feature definition and second feature data may be generated according to the second feature definition based at least in part on the prediction request.

Abstract: In one aspect, a playback deice is configured to identify in an audio stream, via a second wake-word engine, a false wake word for a first wake-word engine that is configured to receive as input sound data based on sound detected by a microphone. The first and second wake-word engines are configured according to different sensitivity levels for false positives of a particular wake word. Based on identifying the false wake word, the playback device is configured to (i) deactivate the first wake-word engine and (ii) cause at least one network microphone device to deactivate a wake-word engine for a particular amount of time. While the first wake-word engine is deactivated, the playback device is configured to cause at least one speaker to output audio based on the audio stream. After a predetermined amount of time has elapsed, the playback device is configured to reactivate the first wake-word engine.