Abstract: A control method for a display system is provided. The display system includes a display device displaying an image, and a voice processing device which generates first voice data based on a first voice requesting a first-type operation belonging to a part of a plurality of types of operations to the display device and transmits the first voice data to a server device. The display device receives a command to execute the first-type operation from the server device. The display device includes a voice recognition unit recognizing a second voice requesting a second-type operation that is different from the first-type operation, and a control unit controlling execution of the first-type operation and the second-type operation. The voice processing device transmits the first voice data requesting a permission for the execution of the second-type operation, to the server device. The display device receives a command permitting the execution of the second-type operation from the server device.

Abstract: A system and method implemented on a computing device for analyzing a digital corpus of unstructured interlocutor conversations to discover intents, goals, or both intents and goals of one or more parties to the conversations, by grouping the conversation utterances according to semantic similarity clusters; selecting the best utterance(s) that mostly likely embody a party's stated goal or intent; creates a set of candidate intent names for each cluster based upon each intent utterance in each conversation in each cluster; rates each candidate intent (or goal) for each intent name; and selects the most likely candidate intent (or goal) name for the purposes of subsequent automation of future conversations such as, but not limited to, automated electronic responses using Artificial Intelligence and machine learning.

Abstract: An electronic apparatus and a control method thereof are provided. A method of controlling an electronic apparatus according to an embodiment of the disclosure includes: receiving input of a first utterance, identifying a first task for the first utterance based on the first utterance, providing a response to the first task based on a predetermined response pattern, receiving input of a second utterance, identifying a second task for the second utterance based on the second utterance, determining the degree of association between the first task and the second task, and setting a response pattern for the first task based on the second task based on the determined degree of association satisfying a predetermined condition. The control method of an electronic apparatus may use an artificial intelligence model trained according to at least one of machine learning, a neural network, or a deep learning algorithm.

Abstract: The disclosure discloses a method and an apparatus for training a dialog generation model, and a dialog generation method and apparatus, and relates to the field of artificial intelligence. The method includes: encoding a context sample to obtain a first latent variable, and recognizing the first latent variable to obtain a prior latent variable; encoding a response sample to obtain a second latent variable; encoding a response similar sample to obtain a third latent variable; performing recognition according to a Gaussian mixture distribution of the first latent variable, the second latent variable, and the third latent variable to obtain a posterior latent variable; and matching the prior latent variable with the posterior latent variable, and performing adversarial training on a dialog generation model.

Abstract: A voice command resolution apparatus, including a memory configured to store instructions; and a processor configured to execute the instructions to: recognize a voice command of a user in an input sound, analyze a non-speech sound included in the input sound, and determine at least one target Internet of things (IoT) device related to execution of the voice command, based on an analysis result of the non-speech sound.

Abstract: Disclosed is a method and apparatus for processing a speech. The method includes obtaining context information from a speech signal of a user using a neural network-based encoder, determining, based on the context information, attention information corresponding to a segment included in the speech signal, and recognizing, based on the attention information, the segment by decoding a portion of the context information identified as corresponding to the segment.

Abstract: This disclosure describes techniques and systems for encoding instructions in audio data that, when output on a speaker of a first device in an environment, cause a second device to output content in the environment. In some instances, the audio data has a frequency that is inaudible to users in the environment. Thus, the first device is able to cause the second device to output the content without users in the environment hearing the instructions. In some instances, the first device also outputs content, and the content output by the second device is played at an offset relative to a position of the content output by the first device.

Abstract: Computer-implemented methods for training a neural network, as well as for implementing audio encoders and decoders via trained neural networks, are provided. The neural network may receive an input audio signal, generate an encoded audio signal and decode the encoded audio signal. A loss function generating module may receive the decoded audio signal and a ground truth audio signal, and may generate a loss function value corresponding to the decoded audio signal. Generating the loss function value may involve applying a psychoacoustic model. The neural network may be trained based on the loss function value. The training may involve updating at least one weight of the neural network.

Abstract: There is provided a voice orchestrated infrastructure system which includes a hub in communication with at least one endpoint device located in a room or area, and the at least one endpoint device is in communication with the hub and at least one endpoint device in a second room or area through the hub. The hub includes a set of non-transitory commands which when executed with a central processor the at least one endpoint device is activated and controlled by voice commands which are independent of service provider type. The hub includes a non-transitory computer-readable storage medium which stores computer-executable instructions that, when executed by a processor, cause the processor to perform operations for determining the voice command which is communicated to and from the at least one end point device.

Abstract: Various embodiments of the present disclosure relate to a method for providing an intelligent assistance service and an electronic device for performing the same. According to an embodiment, an electronic device comprises at least one communication circuit, at least one microphone, at least one speaker, at least one processor operatively connected to the communication circuit, the microphone, and the speaker, and at least one memory electrically connected to the processor, wherein the memory has instructions stored therein which, when executed, cause the processor to receive a wake-up utterance calling a voice-based intelligent assistance service, in response to the wake-up utterance, to identify a session which is in progress by the voice-based intelligent assistance service, and, upon receiving a control command, to provide the control command to an external device through the session on the basis of the session. Other embodiments are also possible.

Abstract: A spoofing detection apparatus 100 includes a multi-channel spectrogram creation unit 10 and an evaluation unit 40. The multi-channel spectrogram creation unit 10 extracts different type of spectrograms from speech data and integrates the different type of spectrograms to create a multi-channel spectrogram. The evaluation unit 40 evaluates the created multi-channel spectrogram by applying the created multi-channel spectrogram to a classifier constructed using labeled multi-channel spectrograms as training data and classifies it to either genuine or spoof.

Abstract: Techniques for prioritizing resources of various users, associated with a device, when responding to a user input received from the device are described. When a user input is received from a device, a system may generate a resource list for a group profile (e.g., a household profile) and each user profile (including any guest user profile) associated with the device. Each resource list may include the catalogs of resources (e.g., songs of a playlist, contacts of a contact list, etc.) of the group profile or user profile. The system may also generate a weight matrix including a respective weight for each catalog of each resource list. Various processing components (e.g., an automatic speech recognition component, a natural language understanding component, and an entity resolution component) may process using the resource lists and the weight matrix to determine an output responsive to the user input.

Abstract: Methods, apparatus, systems, and computer-readable media are provided for transferring dialog sessions between devices using deep links. The dialog sessions can correspond to interactions, mediated by an automated assistant, between a user and a third party application. During the dialog session, a user can request that the dialog session be transferred to a different device, for example, to interact with the third party application through a different modality. In response, the automated assistant and/or the third party application can generate a link that can be transferred to the transferee device to allow the transferee device to seamlessly take over the dialog session. In this way, computational resources and electrical power can be preserved by not requiring a recipient device to re-process natural language inputs previously provided during the dialog session.

Abstract: In one aspect, a playback device includes a command-keyword engine having a local natural language unit (NLU). The playback device detects, via the command-keyword engine, a first command keyword in voice input of sound detected by one or more microphones of the playback device. The playback device determines whether the sound input data includes a keyword from a first predetermined library of keywords via a local natural language unit (NLU). The playback device transmits the input sound data to a second playback device over a local area network, the second playback device employing a second local NLU with a second predetermined library of keywords. The playback device receives a response from the second playback device and performs an action based on an intent determined by at least one of the first NLU or the second NLU according to the keywords in the voice input.

Abstract: A method, computer system, and a computer program product for digital remote presentation are provided. Presentation content is received that includes visual content, one or more speech triggers, and one or more presentation enhancements corresponding to the one or more speech triggers. A virtual meeting is presented by transmitting the presentation content to at least one receiver computer. A first audio file is received that includes recorded audio spoken by a presenter during the virtual meeting. From the first audio file the one or more speech triggers spoken by the presenter are identified. The respective presentation enhancement corresponding to the identified speech trigger is performed. The presentation enhancement is presented to the at least one receiver computer during the virtual meeting.

Abstract: An electronic device is provided. The electronic device includes a memory for storing at least one dynamic shortcut command, a display, and a processor operatively connected with the memory and the display, the processor configured to store a first dynamic shortcut command including first type information for at least one first dynamic variable word in the memory, when acquiring a user utterance, detect the first dynamic shortcut command in the memory based on the first dynamic variable word included the user utterance, change the first type information included in the detected first dynamic shortcut command into the first dynamic variable word included in the user utterance, and execute a task corresponding to the changed first dynamic shortcut command including the first dynamic variable word included in the user utterance. Various other embodiments may be provided. The method performing shortcut command in the electronic device may be performed using an artificial intelligence model.

Abstract: Methods, electronic devices, and storage media for driving an interaction object are provided. The methods include: obtaining an audio signal at a periphery of a display device; obtaining, based on the audio signal, first driving data for driving the interaction object to respond; monitoring, in response to outputting the first driving data, the audio signal for detecting a sound of a target object; and driving, based on a presence state of the sound of the target object in the audio signal, the interaction object to respond.

Abstract: Techniques for providing device functionalities using device components are described. A system receives a system-generated directive from a skill system and determines a workflow to execute. The system implements a response orchestrator that operates based on the workflow that includes interception points where cross-cutting functionalities can be invoked as pluggable components. The interception points occur pre-system-generated directive, pre-device-facing directive, post-device-facing directive generation, post-device-facing directive dispatch, and the like. The system supports asynchronous execution, conditional execution, and sequential execution of components. Data determined by the cross functionality components can be used by other components for processing.

Abstract: Systems and methods for natural language processing policies are disclosed. For example, content such as a response to a user command and/or user input such as a customer review, may be analyzed to determine if the content deviates from one or more content policies and to determine a severity of the content-policy deviation(s). A system may determine a number of content-policy deviations associated with the content and whether the content includes an indicator of a person, such as a pronoun and/or a proper noun. Content that includes multiple content-policy deviations and/or than includes an indicator of a person may be determined to be more severe than other deviated content. Applications associated with deviated content may be ranked and corrective action may be taken based on the ranking.

Abstract: A messaging system, which hosts a backend service for an associated messaging client, includes a voice chat system that provides voice chat functionality that enables users to dictate their messages, while delivering the resulting message to the intended recipient as both the associated audio and text content. When a user at a sender client device begins dictating a voice message, the voice chat system starts converting the received audio stream into text and, also, starts communicating the audio content together with the generated text to the recipient client device. The recipient user can listen to the voice message and read the text generated from the audio in real time. It is also possible for the recipient user to consume the voice message in a textual form only, if the sound at the client device is undesirable.