Validating actions in a digital assistant-based application is provided. The system identifies an application with a conversational interface. The system selects an action from an action repository and generates, via a natural language processor, a trigger phrase for input into the application. The system executes the application to process the trigger phrase to identify an action of the application. The system identifies a parameter used by the application to execute the action, and generates, based on the parameter and via execution of the conversational interface of the application, a first query responsive to the trigger phrase. The system generates a first response to the first query for input into the application. The system determines, based on execution of the application to process the first response, a state of the application. The system evaluates the state to determine an error code and provide a notification based on the error code.

Disclosed are method and apparatus for correcting voice dialogue, including: recognizing first text information of a dialogue speech input by a user, including a first semantic keyword determined from a plurality of candidate terms; feeding back a first result with the first semantic keyword to the user based on the first text information; feeding back the plurality of candidate terms to the user in response to the user's selection of the first semantic keyword from the first result; and receiving a second semantic keyword input by the user, correcting the first text information based on the second semantic keyword, determining corrected second text information, and feeding back a second result with the second semantic keyword to the user based on the second text information. The problem of true ambiguity can be solved, while improving the fault tolerance and processing capability of the dialogue apparatus for corresponding errors.

A method and apparatus for formulating a query by a digital assistant is provided herein. During operation a digital assistant will receive a query from a user. The query will have a type of device mentioned within the query. In response, the digital assistant will listen for any nearby device to announce itself. The query will then be modified by the digital assistant to include a device identification heard in the announcement. Results from the modified query will be provided to the user.

In one embodiment, a method includes receiving at a head-mounted device a speech input from a user and a visual input captured by cameras of the head-mounted device, wherein the visual input comprises subjects and attributes associated with the subjects, and wherein the speech input comprises a co-reference to one or more of the subjects, resolving entities corresponding to the subjects associated with the co-reference based on the attributes and the co-reference, and presenting a communication content responsive to the speech input and the visual input at the head-mounted device, wherein the communication content comprises information associated with executing results of tasks corresponding to the resolved entities.

An electronic apparatus is provided. The electronic apparatus includes a communication interface with communication circuitry, a memory configured to store at least one instruction and a processor, and the processor is configured to receive a first audio recognized as a wake up word by an external device from the external device, determine whether the first audio corresponds to the wake up word by analyzing the first audio, based on determining that the first audio does not correspond to the wake up word, obtain a neural network model for detecting a wake up word misrecognition based on the first audio, and transmit information regarding the neural network model to the external device.

Methods and systems for performing at least one audio activity (e.g., conducting a phone call or playing music or other audio content) in an environment including by determining an estimated location of a user in the environment in response to sound uttered by the user (e.g., a voice command), and controlling the audio activity in response to determining the estimated user location. The environment may have zones which are indicated by a zone map and estimation of the user location may include estimating in which of the zones the user is located. The audio activity may be performed using microphones and loudspeakers which are implemented in or coupled to smart audio devices.

Embodiments of the present disclosure provide an interactive method of a robot, an interactive device of a robot and a device. The method includes: obtaining voice information input by an interactive object, and performing semantic recognition on the voice information to obtain a conversation intention; obtaining feedback information corresponding to the conversation intention based on a conversation scenario knowledge base pre-configured by a simulated user; and converting the feedback information into a voice of the simulated user, and playing the voice to the interactive object.

An artificial intelligence that registers users to a common distributed computing platform that provides access to a plurality of voice assistants. A first command issued by a user is received by a first voice assistant of the plurality of voice assistants at a first location. A context database is built by storing the at least the first command on the distributed computing platform. A second command issued by the user is received by a second voice assistant of the plurality of first assistants at a second location. A context assigning engine on the common distributed computing platform analyzes the second command in comparison with the at least the first command on the context database. Similarity between the first command and the second command provides context. The second voice assistant receiving the context from the context assigning engine employs the context to answer the second command.

Artificial assistant system notification techniques are described that overcome the challenges of conventional search techniques. In one example, a user profile is generated to describe aspects of products or services learned through natural language conversations between a user and an artificial assistant system. These aspects may include price as well as non-price aspects such as color, texture, material, and so forth. To learn the aspects, the artificial assistant system may leverage spoken utterances and text initiated by the user as well as learn the aspects from digital images output as part of the conversation. Once generated, the user profile is then usable by the artificial assistant system to assist in subsequent searches.

In one embodiment, a method includes receiving an initial input in a first modality from a first user from a client system associated with the first user, determining one or more intents corresponding to the initial input by an intent-understanding module, generating one or more candidate continuation-inputs based on the one or more intents, where the one or more candidate continuation-inputs are in one or more candidate modalities, respectively, and wherein the candidate modalities are different from the first modality, and sending instructions for presenting one or more suggested inputs corresponding to one or more of the candidate continuation-inputs to the client system.