An electronic device, computer program product, and method avoids presenting certain objects during a video communication session. During a video communication session with second electronic device(s), a controller of an electronic device identifies baseline image(s) from an image stream provided by an image capturing device of the electronic device. The baseline image includes a primary image portion of participant(s) and including a scene of objects within the foreground or background of participant (s), during an initial portion of the video communication session. The controller monitors the image stream for a subsequent detection of the primary image portion and of non-participant(s) or object(s) as a secondary image portion that is not included within the baseline image(s). The controller responds to detecting the secondary image portion subsequently appearing within the image stream by communicating, to the one or more second electronic devices, a substitute image stream that does not present the secondary image portion.

An in-vehicle speech interaction method and a device are provided. The method includes: obtaining user speech information; determining a user instruction based on the user speech information; determining, based on the user instruction, whether response content to the user instruction is privacy-related; and determining, based on whether the response content is privacy-related, whether to output the response content in a privacy protection mode, to protect privacy from being leaked.

An in-vehicle speech interaction method and a device are provided. The method includes: obtaining user speech information; determining a user instruction based on the user speech information; determining, based on the user instruction, whether response content to the user instruction is privacy-related; and determining, based on whether the response content is privacy-related, whether to output the response content in a privacy protection mode, to protect privacy from being leaked.

Disclosed herein are system, method, and computer program product embodiments for machine learning systems to process incoming call-center calls based on inferred sentiments. An incoming call is routed to a call agent based on an inferred topic, classified based on one or more inferred sentiments of a current caller's speech, determining, based on the call classification, that a complaint has been articulated and initiating an automated assistance by searching for one or more similar callers to the current caller. Based on finding a successful call outcome associated with one or more similar callers, the system suggests one or more phrases to the call agent for use in a dialog with the current caller to improve the one or more inferred sentiments.

Disclosed herein are system, method, and computer program product embodiments for machine learning systems to process incoming call-center calls based on inferred sentiments. An incoming call is routed to a call agent based on an inferred topic, classified based on one or more inferred sentiments of a current caller's speech, determining, based on the call classification, that a complaint has been articulated and initiating an automated assistance by searching for one or more similar callers to the current caller. Based on finding a successful call outcome associated with one or more similar callers, the system suggests one or more phrases to the call agent for use in a dialog with the current caller to improve the one or more inferred sentiments.

Techniques are described for a contextual natural language understanding (cNLU) framework that is able to incorporate contextual signals of variable history length to perform joint intent classification (IC) and slot labeling (SL) tasks. A user utterance provided by a user within a multi-turn chat dialog between the user and a conversational agent is received. The user utterance and contextual information associated with one or more previous turns of the multi-turn chat dialog is provided to a machine learning (ML) model. An intent classification and one or more slot labels for the user utterance are then obtained from the ML model. The cNLU framework described herein thus uses, in addition to a current utterance itself, various contextual signals as input to a model to generate IC and SL predictions for each utterance of a multi-turn chat dialog.

An electronic apparatus is provided. The electronic apparatus includes a microphone, a memory configured to store a plurality of keyword recognition models, and a processor, which is coupled with the microphone and the memory, configured to control the electronic apparatus, wherein the processor is configured to selectively execute at least one keyword recognition model among the plurality of keyword recognition models based on operating state information of the electronic apparatus, based on a first user voice being input through the microphone, identify whether at least one keyword corresponding to the executed keyword recognition model is included in the first user voice by using the executed keyword recognition model, and based on at least one keyword identified as being included in the first user voice, perform an operation of the electronic apparatus corresponding to the at least one keyword.

An in-vehicle apparatus is connectable to a device that includes a voice assistant function. The in-vehicle apparatus includes: a voice detector that performs voice recognition of an audio signal input from a microphone and that controls functions of the in-vehicle apparatus based on a result of the voice recognition; and an interface that communicates with the device. When being informed of a detection of a predetermined word in the audio signal as the result of the voice recognition of the audio signal performed by the voice detector, the interface sends to the device, not via the voice detector, the audio signal input from the microphone. The predetermined word is for activating the voice assistant function of the device.

An in-vehicle apparatus is connectable to a device that includes a voice assistant function. The in-vehicle apparatus includes: a voice detector that performs voice recognition of an audio signal input from a microphone and that controls functions of the in-vehicle apparatus based on a result of the voice recognition; and an interface that communicates with the device. When being informed of a detection of a predetermined word in the audio signal as the result of the voice recognition of the audio signal performed by the voice detector, the interface sends to the device, not via the voice detector, the audio signal input from the microphone. The predetermined word is for activating the voice assistant function of the device.

An artificial intelligence device includes a microphone configured to receive a speech command, a speaker, a communication unit configured to perform communication with an external artificial intelligence device, and a processor configured to receive a wake-up command through the microphone, acquire a first speech quality level of the received wake-up command, receive a second speech quality level of the wake-up command input to the external artificial intelligence device from the external artificial intelligence device through the communication unit, output a notification indicating that the artificial intelligence device is selected as an object to be controlled through the speaker, when the first speech quality level is larger than the second speech quality level, receive an operation command through the microphone, acquire an intention of the received operation command and transmit the operation command to an external artificial intelligence device which will perform operation corresponding to the operation command according to the acquired intention through the communication unit.