Abstract: A system implements a dynamic word correlated topic model (DWCTM) to model an evolution of topic popularity, word embedding, and topic correlation within a set of documents, or other dataset, that spans a period of time. For example, the DWCTM receives the set of documents and a quantity of topics for modeling. The DWCTM processes the set computing, for each topic, various distributions to capture a popularity, word embedding, and correlation with other topics across the period of time. In other examples, a dataset of user listening sessions comprised of media content items for modeling by the DWCTM. Media content metadata (e.g., artist or genre) of the media content items, similar to words of a document, can be modeled by the DWCTM.

Abstract: A server system receives, from a first client device, a video recording created by the first client device and an indication that the video recording is to be associated with a media content item. The server system retrieves text associated with the media content item and provides the text for display at the first client device as a text lens overlay that is mapped to a portion of an object in the video recording of the first client device and follows movement of the portion of an object in the video recording created by the first client device. The server system provides, to a second client device, the video recording in combination with the media content item; and the text associated with the media content item as the text lens overlay that is mapped to the portion of the object of the first client device.

Abstract: One aspect herein relates to a method performed by a server system. In response to receiving a request message from a first electronic device, an audio content item is retrieved and a non-static content item associated with the audio content item is located. The server system transmits, to the first electronic device, the audio content item, and the located non-static media content item. The server system receives a second request message from a second electronic device, the second request message including an instruction for the server system to modify the non-static media content item associated with the audio content item. In response to the second request message, the server system modifies the non-static media content item associated with the audio content item in accordance with the instruction of the second request message from the second electronic device.

Abstract: A text-to-speech synthesis method comprising: receiving text; inputting the received text in a prediction network; and generating speech data, wherein the prediction network comprises a neural network, and wherein the neural network is trained by: receiving a first training dataset comprising audio data and corresponding text data; acquiring an expressivity score for each audio sample of the audio data, wherein the expressivity score is a quantitative representation of how well an audio sample conveys emotional information and sounds natural, realistic and human-like; training the neural network using a first sub-dataset, and further training the neural network using a second sub-dataset, wherein the first sub-dataset and the second sub-dataset comprise audio samples and corresponding text from the first training dataset and wherein the average expressivity score of the audio data in the second sub-dataset is higher than the average expressivity score of the audio data in the first sub-dataset.

Abstract: Methods, systems and computer program products are provided for performing personalization. A segments reader receives a request for episode metadata corresponding to an episode. A determination is made whether the episode metadata should be personalized to an account associated with the request. In turn, personalized-episode metadata associated with the account and the request is retrieved and the personalized-episode metadata is provided to a client device associated with the request.

Abstract: Simulator augmented content selection is provided by initializing a content selection object according to session initialization parameter values associated with a simulated media content playback session. The content selection object corresponds to a candidate content selection machine learning model trained to predict selectable content media items for at least one simulated user. A simulated session including a sequence of predicted simulated user next actions and one or more predicted sets of selectable content items are generated by applying a simulated user model to content items identified by the initialized content selection object, where the simulated user model is trained to predict a next action of the simulated user in response to a simulated playback input received from the simulated user and each set of the selectable content items are correlated to each next action in the sequence of predicted simulated user next actions.

Abstract: An electronic device obtains a collection of images and obtains a media item. The electronic device selects a subset of the collection of images, including: selecting an initial subset of the collection of images, wherein the initial subset of the collection of images is based on descriptors associated with the collection of images and/or the media item; obtaining a set of preferences for a user of the media-providing service; and selecting the subset of the collection of images from the initial subset of the collection of images based on the set of preferences for the user of the media-providing service. The electronic device concurrently presents: a respective image of the subset of the collection of images; and the media item.

Abstract: Systems, devices, and methods for identifying media content using indirect qualities are provided. An example media-delivery system includes a content identification engine that applies a model associated with an indirect quality to media content items to generate indirect quality scores for the media content items, filters the media content items based on metadata associated with the media content items to generate filtered media content items, and presents at least some of the filtered media content items based on the indirect quality scores. An example media-playback device includes a search control engine that presents a search interface with a user-actuatable control for specifying a value of an indirect quality for use as a search criteria, transmits the search criteria to a media-delivery service, and receives media content items matching the search criteria from the media-delivery service, wherein the media content items are identified using a statistical model.

Abstract: A system for device-to-device media capturing is described herein. An example system includes a media delivery system of a media service and at least a first and second device associated with respective first and second user accounts of the media service. The first device is also associated with an active media content item provided by the media delivery system that is automatically captured by the second device. For example, as the second device is moved proximate to the first device, one or more wireless communications are transmitted between the devices that trigger device-to-device media capturing. Resultantly, an identifier for the active media content item is stored to a library of the second user account of the media service. The identifier is stored in response to detecting the proximity of the devices and determining that the second device is moving towards the first device.

Abstract: A media system includes: a media-playback device including: a media-output device that plays media content items; and a tempo control engine to: select media content based upon suitability for a repetitive-motion activity; place each media content item from the media content into two or more pools of media content, with a first pool including media content which the user has previously indicated as being relevant, and a second pool including media content that the user has not previously indicated as being relevant; and sort the media content in each of the first pool and the second pool based upon tempo.

Abstract: A system for processing voice requests includes a voice assistant manager and a plurality of voice assistants. The voice assistant manager detects a wake word in an utterance and communicates the utterance to a voice assistant of the plurality of voice assistants. In some embodiments, the voice assistant may verify the detected wake word and communicate with a cloud service, which may also verify the detected wake word and generate a response to the utterance. In some embodiments, the voice assistant manager may activate or deactivate one or more of the voice assistants.

Abstract: A method for managing voice assistants is disclosed. The method may be performed by a voice assistant controller communicatively coupled to a plurality of voice assistants. The voice assistant controller may determine a first order of the plurality of voice assistants. Based at least in part on the first order, the voice assistant controller may activate one or more voice assistants. Furthermore, the voice assistant controller may determine a second order of the plurality of voice assistants. Based at least in part on the second order, the voice assistant controller may suspend an active assistant, activate a suspended assistant, or perform both operations.

Abstract: A training audio track feature vector is generated for training audio tracks. The training audio track feature vector includes training track vector components based on one or more feature sets. Each of the training track vector components is grouped into at least one cluster. Audio filters are mapped to one or more of the clusters, thereby building a feature-filter mapping function. Mapping functions from filters to audio output devices and/or physical space acoustic features can also be built. A media playback device receives the mapping function(s) and is enabled to apply the mapping function(s) to a query audio track feature vector to identify at least one audio filter corresponding to the query audio track. The media playback device can then apply the at least one audio filter to the query audio track.

Abstract: A method for processing voice input is disclosed. The method may be performed by a device including a voice assistant manager and a plurality of voice assistants. In some embodiments, the method includes receiving an utterance from a user, detecting a category of the utterance, and communicating the utterance to a selected voice assistant of the plurality of voice assistants. The selected voice assistant may be associated with the detected category. In some embodiments, the selected voice assistant may generate a response to utterance, and the response may be output to the user.

Abstract: A system for multi-track playback of media content includes: a media device; a user interface, provided at the media device, which displays a visual array of media options, a playback logic, provided within the media device, which is configured so that, while a selected point or region is determined by the user interface as being moved in response to user input, within the visual array of media options, the system determines media options that are proximate to the selected point or region, and adjusts playback parameters for corresponding media content items, by crossfading or otherwise combining playback to reflect the media options relative distances from the selected point or region; and a tempo logic, provided within the media device, which is configured to provide or receive a selected tempo and provide the one or more media content items associated with the selected tempo.

Abstract: A parse arbitrator receives a rule-based parser predictive test result indicating whether a first <intent, slots> set contains at least one predictive slot and a descriptive classifier test result indicating whether the digitized descriptive query is descriptive. The parse arbitrator instructs a fulfillment system to perform a fulfillment operation based on the first <intent, slots> set when the rule-based parser predictive test result and the descriptive classifier test result align and instructs a fulfillment system to perform a fulfillment operation based on a second <intent, slots> set when the rule-based parser predictive test result and the descriptive classifier test result do not align. The first <intent, slots> set has been generated by using a first parser to parse a digitized descriptive query and the second <intent, slots> set has been generated by using a second parser to parse the digitized descriptive query.

Abstract: Systems, methods, and devices for training and testing utterance based frameworks are disclosed. The training and testing can be conducting using synthetic utterance samples in addition to natural utterance samples. The synthetic utterance samples can be generated based on a vector space representation of natural utterances. In one method, a synthetic weight vector associated with a vector space is generated. An average representation of the vector space is added to the synthetic weight vector to form a synthetic feature vector. The synthetic feature vector is used to generate a synthetic voice sample. The synthetic voice sample is provided to the utterance-based framework as at least one of a testing or training sample.

Abstract: Technology for generating, reading, and using machine-readable codes is disclosed. There is a method, performed by an image capture device, for reading and using the codes. The method includes obtaining an image, identifying an area in the image having a machine-readable code. The method also includes, within the image area, finding a predefined start marker defining a start point and a predefined stop marker defining a stop point, an axis being defined there between. A plurality of axis points can be defined along the axis. For each axis point, a first distance within the image area to a mark is determined. The distance can be measured from the axis point in a first direction which is orthogonal to the axis. The first distances can be converted to a binary code using Gray code such that each first distance encodes at least one bit of data in the code.

Abstract: A system for device discovery for social playback is disclosed. The system operates to connect a host media playback device to a media output device and broadcast a social playback session to guest media playback devices. Upon joining a social playback session, a guest media playback device may control the media playback at the host media playback device. Where the media output for the social playback session is provided by the media output device.