Abstract: Systems and methods for skipping to playback positions in media content using seek guides are provided. Seek guides may be associated with a media content item. Each seek guide may have a position and a radius. When a user skips to a reference position, a seek guide selector may select a seek guide to use in setting a new playback position. The seek guide selector may use a probabilistic distribution positioned based on the reference position to select a seek guide. Probabilities may be calculated for each seek guide using a cumulative distribution function, and the seek guides may be ranked based on the calculated probabilities. A seek guide may be selected based on the ranking, and a new playback position may be set based on the position of the selected seek guide.

Abstract: Systems and methods for teaching a user a language using media content are provided. Translation prompts may be automatically presented to the user as the user listens to music on a computing device. The translation prompts may present a question to the user asking the user to translate a lyric in the music. The translation prompts may be personalized for the user based on the user's skill level and language learning needs. Music may also be selected for the user based on the user's music taste and the music having lyrics that are appropriate for the user's skill level and language learning needs.

Abstract: An electronic device identifies a set of seed content items that correspond to violative content items. The electronic device determines, using playback histories indicating consumption of respective content items, connections between a respective content item and a first audience that has consumed the respective content item and that has consumed at least a threshold number of seed content items from the set of seed content items. The electronic device provides information corresponding to the connections as an input to a machine learning model. The electronic device receives, as an output from the machine learning model, likelihoods that respective content items are violative content items and stores a set of content items, selected using the output from the machine learning model, as candidate content items in accordance with a determination that the content item satisfies likelihood criteria.

Abstract: Media content episodes are received. Using machine learning, one or more media segments of interest are identified in each of the media content episodes based at least in part on an analysis of content included in a corresponding audio content episode. Each of the identified media segments is associated with one or more automatically determined tags. Using machine learning, a recommended media segment is selected for a specific user from the identified media segments based at least in part on attributes of the specific user and the automatically determined tags of the identified media segments. The recommended media segment is automatically provided in an media segment feed.

Abstract: While a first media content item from a shared playback session is being presented on a set of presentation devices, each of the set of presentation devices corresponding to a respective user of a plurality of users in the shared playback session, a master device receives a request to modify playback of the shared playback session from an observer device of a set of observer devices that corresponds to a presentation device for a first user, wherein the set of observer devices is different from the set of presentation devices. In response to the request to modify playback of the shared playback session, the master device sends a command for an action selected based on the request to each of the set of presentation devices.

Abstract: A system for refinement of a voice query interpretation interprets a voice query received at a voice-enabled device to identify commands responsive to the voice query for execution at the voice-enabled device, and enables refinement of the interpretation of the voice query through a graphical user interface generated and displayed at a GUI-capable device. The graphical user interface includes a set of selectable options relating to the voice query and identifying a refinement of the interpretation of the voice query to enable control and/or adjustment of commands to be executed by the voice-enabled device. For example, if one of the selectable options is selected, then a command associated with the selected option is identified and executed by the voice-enabled device.

Abstract: Apparatus, methods and computer-readable medium are provided for processing wind noise. Audio input is processed by receiving an audio input. A wind noise level representative of a wind noise at the microphone array is measured using the audio input and a determination is made, based on the wind noise level, whether to perform either (i) a wind noise suppression process on the audio input on-device, or (ii) the wind noise suppression process on the audio input on-device and an audio reconstruction process in-cloud.

Abstract: An electronic device stores, for a user of a media-providing service, a playback history that includes information about media items that have previously been consumed by the user. The electronic device receives a request to search for media content including search criteria. In response to the request, and without additional user intervention, the electronic device generates a vector representation of the user using media items from the playback history of the user that are relevant to the search criteria. The electronic device identifies one or more media content items from a media content library that match the vector representation of the user and the search criteria and provides, to the user, the one or more media content items.

Abstract: Systems, devices, apparatuses, components, methods, and techniques for predicting user and media-playback device states are provided. Systems, devices, apparatuses, components, methods, and techniques for representing cached, user-selected, and streaming content are also provided.

Abstract: An electronic device generates a score for each objective in a hierarchy of objectives. Generating the score comprises, using a first machine learning algorithm, generating a score for a first objective corresponding to a first level in the hierarchy of the objectives and using an output of the first machine learning algorithm, distinct from the score for the first objective, as an input to a second machine learning algorithm to generate a score for a second objective corresponding to a second level in the hierarchy of objectives. The electronic device generates a combined score using the score for the first objective and the score for the second objective. The electronic device selects, automatically without user input, media content based on the combined scores for the plurality of media content items and streams, using an application of the media-providing service, one or more of the selected media content to a user.

Abstract: A media content steering solution is provided to identify a user query to steer playback of media content that is currently playing or has been played. The user steering query can include a voice request for playing media content that is relatively different from the media content being currently played or having been played. The media content steering solution analyzes the utterance of the user query and uses it to identify such different content that satisfies the user intent contained in the user query.

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 method is provided for initiating a first shared playback session at a first device of a host user. The method includes, in response to receiving the request from the second device: in accordance with a determination that the second device is a first type of device, providing, to the second device, a first joining method for joining the first shared playback session and in accordance with a determination that the second device is a second type of device, providing, to the second device, a second joining method, distinct from the first joining method for joining the first shared playback session.

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: 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: 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: 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: 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.