Abstract: In some embodiments, a content analysis system accesses input content associated with a user of an online platform. The content analysis system extracts entity tags for entities contained in the input content and links the identities to standard entities in a knowledge base to generate linked entities. The content analysis system further generates a knowledge graph to include the linked entities and other standard entities connected to the linked entities as nodes and edges connecting these nodes. Based on the knowledge graph, the content analysis system identifies related entities that are similar to the linked entities and cause the online platform to be modified based on the related entities.

Abstract: Systems (100) and methods (800) for communicating information. The methods comprise: storing message sets in Communication Devices (“CDs”) so as to be respectively associated with speaker information; performing operations, by a first CD, to capture an audio message spoken by an individual and to convert the audio message into a message audio file; comparing the message audio file to each reference audio file in the message sets to determine whether one of the reference audio files matches the message audio file by a certain amount; converting the audio message into a text message when a determination is made that a reference audio file does match the message audio file by a certain amount; generating a secure text message by appending the speaker information that is associated with the matching reference audio file to the text message, or by appending other information to the text message; transmitting the secure text message.

Abstract: In general, user interfaces for controlling a plurality of multimedia players in groups are disclosed. According to one aspect of the present invention, a user interface is provided to allow a user to group some of the players according to a theme or scene, where each of the players is located in a zone. When the scene is activated, the players in the scene react in a synchronized manner. For example, the players in the scene are all caused to play a multimedia source or music in a playlist, wherein the multimedia source may be located anywhere on a network. The user interface is further configured to illustrate graphically a size of a group, the larger the group appears relatively, the more plays there are in the group.

Abstract: Example methods and systems for modifying the playback of content using pre-processed profile information are described. Example instructions, when executed, cause at least one processor to access a media stream that includes media and a profile of equalization parameters, the media stream provided to a device via a network, the profile of equalization parameters included in the media stream selected based on a comparison of a reference fingerprint to a query fingerprint generated based on the media, the profile of equalization parameters including an equalization parameter for the media; and modify playback of the media based on the equalization parameter specified in the accessed profile.

Abstract: Technology for grouping, consolidating, and pairing individual playback devices with network capability (players) to stimulate a multi-channel listening environment is disclosed. An example method includes receiving an audio signal containing a range of audio frequencies; amplifying, according to a gain parameter, the audio signal to be reproduced by at least one speaker. The example method includes automatically increasing the gain parameter to a higher gain parameter responsive to a determination that no more than a subset of the range of audio frequencies is to be reproduced by the at least one speaker. The example method includes amplifying, according to the higher gain parameter, the audio signal containing no more than the subset of the range of audio frequencies to be reproduced by the at least one speaker.

Abstract: Embodiments are described herein that involve a computing device initiating playback of a particular media item on a media playback system that is registered to a particular account of a social media service. The computing device may query the social media service for one or more accounts of the social media service that are registered to respective media playback systems that have played the particular media item on at least a threshold number of occasions and have not yet been connected to the particular account of the social media service within the social network. The computing device may receive the queried one or more accounts of the social media service and cause a graphical interface to display one or more respective selectable indications of the received one or more accounts of the social media service.

Abstract: An example playback device includes a first interface for receiving a first audio signal from a first audio source; a second interface for receiving a second audio signal from a second audio source; and a processor configured to: cause the playback device to playback the second audio signal; determine that the first audio signal is present at the first interface; in response to determining that the first audio signal is present at the first interface, (i) cease playback of the second audio signal being played by the playback device and (ii) cause the playback device to playback the first audio signal; receive an instruction to stop the playback device from playing the first audio signal while the first audio signal is still present at the first interface; and arm the playback device such that a subsequent presence of the first audio signal at the first interface causes the playback device to play the first audio signal.

Abstract: Systems, methods, and computer-readable media for providing variable output as a function of disbursed non-audio input are disclosed. The systems and methods may involve at least one processor configured to receive over a network, during a presentation, from a plurality of network access devices, a plurality of non-audio signals corresponding to activations of substitute audio buttons, each of the plurality of non-audio signals having an audio identity. The at least one processor may be configured to process the received plurality of non-audio signals to determine a quantity of non-audio signals corresponding to a specific audio identity. Disclosed embodiments may also involve a lookup in an audio-related data structure to select at least one particular audio file associated with the audio identity and the determined quantity, to output data for causing the at least one particular audio file to be played.

Abstract: A set of partial words is received. At least one partial word in the set of partial words is completed. The set of partial words with the at least one completed partial word is run through a trained deep neural network, the trained deep neural network inferring a word embedding associated with an unfinished word in the set of partial words. An inferred word is determined based on the inferred word embedding associated with the unfinished word. A sentence may be output, which includes at least the completed partial word and the inferred word.

Abstract: In some embodiments, a method comprises receiving audio content comprising left input channel signals and right input channel signals, and generating first and second input signals from the left and right input channel signals. The first input signal is based on a sum of the left and right input channel signals, and the second input signal is based on a difference of the left and right input channel signals. An array transfer function is applied to the first and second input signals to produced audio output signals, which can be provided to a plurality of audio transducers on one or more playback devices.

Abstract: In some aspects, the disclosure is directed to methods and systems for providing a three-dimensional virtual environment with teleconferencing audio and video feeds placed within the environment via three-dimensional virtual avatars, including indications of directional orientation or facing, and with mixing of spatial audio providing directionality and distance cues. By utilizing a three dimensional environment for display of video streams, video streams corresponding to or displayed on avatars that are farther from the viewer appear smaller within the three dimensional view, and thus can be easily downscaled or reduced in resolution or bit rate without adversely affecting the user experience.

Abstract: Systems and methods are provided herein for determining whether to adjust volumes of individual audio components in a media asset based on a type of segment of the media asset that is playing back. A media guidance application may determine that a user is playing back a segment of a media asset. The media guidance application may determine a type corresponding to the segment. The media guidance application may parse a plurality of audio components of the media asset that are playing back during the segment. The media guidance application may determine, for each audio component, whether to adjust the volume playing back during the segment based on the type. For each audio component of the plurality of audio components, in response to determining to adjust the volume, the media guidance application may adjust the volume of the audio component playing back during the segment.

Abstract: A machine may be configured to generate one or more audio fingerprints of one or more segments of audio data. The machine may access audio data to be fingerprinted and divide the audio data into segments. For any given segment, the machine may generate a spectral representation from the segment; generate a vector from the spectral representation; generate an ordered set of permutations of the vector; generate an ordered set of numbers from the permutations of the vector; and generate a fingerprint of the segment of the audio data, which may be considered a sub-fingerprint of the audio data. In addition, the machine or a separate device may be configured to determine a likelihood that candidate audio data matches reference audio data.

Abstract: An audio generation system is provided to enable coordinated control of multiple IoT devices for audio collection and distribution of one or more audio sources according to location and user preference. The audio generation system enables a location sensitive acoustic control of sound, both as a shaped envelope for a particular source, and as an individualized experience. The audio generation system also facilitates an interactive visual system for visualization and manipulation of the audio environment including via the use of augmented reality and/or virtual reality to depict soundscapes. The audio generation system can also facilitate a system for improving and achieving an audio environment (sound influence zone) and an intuitive way to understand where sounds will be heard.

Abstract: Systems and methods are provided that train a machine-learned language encoding model through the use of a contrastive learning task. In particular, the present disclosure describes a contrastive learning task where the encoder learns to distinguish input tokens from plausible alternatives. In some implementations, on each training example the proposed method masks out some subset (e.g., 15%) of the original input tokens, replaces the masked tokens with samples from a “generator” (e.g., which may be a small masked language model), and then trains the encoder to predict whether each token comes from the original data or is a replacement produced by the generator.

Abstract: Disclosed is an electronic device including a communication circuit, a microphone, a memory, speaker, and a processor, in which the processor receives the speech input and transmits first data associated with the speech input to a first server for supporting the speech recognition service, receives second data corresponding to processing of a part of the first data from the first server and outputs the second data at a first time that a first period of time has elapsed after the transmission of the first data, and outputs third data corresponding to processing of the rest of the first data at a second time that a second period of time has elapsed from the first time, while receiving the third data from the first server or a second server for supporting the speech recognition service before the second time.

Abstract: Embodiments are described herein that involve receiving, by a social-media computing system from a media playback system, playback data indicating media that is being played back by the media playback system, where the playback data comprises an indication of at least one zone of the media playback system in which the media is being played back; and based on the received playback data, updating social-media data in a social-media account, where the updated social-media data comprises an indication of the at least one zone in which the media is currently being played back.

Abstract: Example systems and techniques disclosed herein facilitate interoperability between different media playback systems referred to herein as a virtual line-in (VLI) media playback system and a native playback system. When a VLI session is created by a VLI sender, a first native playback device can join a VLI group as a VLI receiver. As a VLI receiver, the first native playback device receives audio content and playback commands from the VLI sender to facilitate synchronous playback with other VLI receivers. At the same time, this native playback device can concurrently operate as a native domain group coordinator of a native domain synchrony group. As the native domain group coordinator, the native playback device translates VLI domain audio, control, and timing signals into the native domain and distributes such signals to native domain group members. In this way, the native domain group members can synchronize their playback with the VLI group.

Abstract: Examples of dynamic bonding of playback devices are disclosed. A disclosed example first playback device includes a shared device identifier to determine that a second playback device is sharable between a first bonded zone and a second bonded zone, the first bonded zone comprising the first playback device, the second bonded zone comprising a second playback device; a device manager to cause the shared playback device to join the first bonded zone; and an adjuster to change a first audio parameter of the first playback device in accordance with the joining of the shared playback device in the first bonded zone, wherein at least one of the shared device identifier, the device manager, or the adjuster is implemented via a processor.

Abstract: An artificial sound source separation method and device are disclosed. The sound source separation method by the artificial sound source separation device based on dictionary learning generates a dictionary matrix by performing dictionary learning, receives an overlapping sound source in which at least two sound sources are mixed and separates a target sound source from the overlapping sound source based on the dictionary matrix; and detecting the target sound source. The dictionary learning may be performed using a K-SVD algorithm. The intelligent computing device configuring a sound source processing device of the present disclosure may be associated with an artificial intelligence module, drone (unmanned aerial vehicle, UAV), robot, augmented reality (AR) devices, virtual reality (VR) devices, devices related to 5G services, and the like.