Abstract: Systems and methods for determining to perform an action of a query using a trained natural language model of a natural language understanding (NLU) system are disclosed herein. A text string corresponding to a prescribed action includes at least a content entity is received. A determination is made as to whether the text string corresponds to an audio input of a first group. In response to determining the text string corresponds to an audio input of a first group, a determination is made as to whether the text string includes an obsequious expression. In response to determining the text string corresponds to an audio input of a first group and in response to determining the text string includes an obsequious expression, a determination is made to perform the prescribed action.

Abstract: The methods and systems described herein leveraging acoustic features of a user to generate and present a personalized content to a user. In one example, the method receives a voice query and determines that the query refers to either a first content item or a second content item. The first content item is associated with a first type assigned with a first score and the second content item is associated with a second entity type assigned with a second score. The method also determines whether the query is from the second entity type. The method ranks the first and the second content items based on this determination and generates for presentation of the first and the second content items based on the ranking. The method also changes the first or the second scores based on this determination and selects one of the first or the second content item for presentation.

Abstract: Systems and methods are disclosed herein for generating new content segments based on object name identification. A content segment may be received from a device and a content structure is generated based on the content segment. The content structure includes objects each having attributes. The system may search a contact database associated with the device to identify a matching entry of the contact database with a particular object. The comparison matches metadata of the matching entry with an attribute of the particular object. Upon matching, the first object is modified to include a name attribute based on the matching metadata of the matching entry. In response to receiving a request using the name of the particular object to create a new content segment, the system inserts the particular object into a new content structure and a new content segment is generated for display from the new content structure.

Abstract: Systems and methods for providing notifications without breaking media immersion. A notification delivery application receives notification data while a media device provides a media asset. In response to receiving the notification data while the media device provides the media asset, the notification delivery application generates a voice model based on a voice detected in the media asset. The notification delivery application converts the notification data to synthesized speech using the voice model and generates, by the media device, the synthesized speech for output at an appropriate point in the media asset based on contextual features of the media asset.

Abstract: Systems and methods are described herein for providing content during reduced streaming quality. Data streaming is susceptible to degradation in quality that adversely affects the delivery of content. For example, sufficient reduction in streaming quality can cause video and audio portions of a data stream to become unsynchronized. The system compares currently streamed video frames to previously received video frames to identify suitable replacement video frames for the currently streamed video frames in the event that the currently streamed video frames are affected by the sufficiently reduced streaming quality.

Abstract: Systems and methods for interactively engaging consumers of a media asset are disclosed. The methods allow selection and personalization of a media asset character's name, voice, or dialogue while the media asset is being consumed. The personalization may be propagated through the entire media asset or additionally to other episodes, sequels, and related media assets by identifying and replacing associated metatags. The system determines whether the media asset is being consumed as a group watch where its members are consuming the media asset from different IP addresses or being consumed by viewers in the same room to determine the type of changes allowed. The methods also present queries to engage the viewer, such as by the character asking them a question, and provide supplemental videos to aid in responding to the queries. The responses to queries may also determine the path a story takes in the media asset.

Abstract: Systems and methods are described for viewing missed media content. A media content stream is received at a user device. A first timestamp is logged, in response to determining a first failure in the receiving of the content stream, indicating when the first failure in the receiving of the content stream to the user device occurred. A second timestamp is logged, in response to determining a first restoration of the receiving of the content stream, indicating when the first restoration in the receiving of the content stream to the user device occurred. A first recorded portion of the media content stream is retrieved. The first recorded portion has a start point corresponding to the first timestamp and an end point corresponding to the second timestamp.

Abstract: Systems and methods are described for a media guidance application (e.g., implemented on a user device) that aggregates related media content, associated with media content selected by a user, by comparing keywords.

Abstract: Systems and methods are provided for determining transition scenes in content and playing back transition scenes as overlays over one or more adjacent scenes. Transition scenes (also referred to as “pause scenes”) are slow-moving scenes, with minimal activity or characters, usually surrounded by two faster paced scenes, that may bore certain viewers such as children or mobile device users. The system may help the content move faster, while ensuring the transition scenes are not skipped. The system may receive content with three sequential scenes A, B, and C, and determine scene B is a transition scene between scene A and scene C. Scene B may be generated as an overlay to one of (or parts of both) scene A and scene C so that all three scenes are viewed but the runtime is shorter, and the content's pace is maintained. The system may also determine which scene to overlay, and determine a screen position for the overlay so as not to, e.g., obscure any characters or activity in the content.

Abstract: Systems and methods provided herein describe dynamically displaying a guide interface element for a customized period of time that is determined based on characteristics of the actual guide interface element to be displayed. In this way, when the timeout of the guide interface element is customized based on characteristics of the guide data, the duration engine allows sufficient time for the viewer to view and react to the guide interface element. Incidents of viewer re-launching of the guide interface element can thus be reduced to improve system processing efficiency and viewing experience.

Abstract: Systems and methods are provided herein for selecting graphics to use as backgrounds of media asset identifiers. To this end, a media guidance application may determine that a media asset identifier is to be generated for display, and may determine whether the user input an explicit preference for a media asset corresponding to the media asset identifier (e.g., the user added the media asset to his watch list). In response to determining that the user input the explicit preference for the media asset corresponding to the media asset identifier, the media guidance application may determine display dimensions of the second media asset identifier, select a graphic that corresponds to the display dimensions, and generate for display the selected graphic as a background graphic of the media asset identifier.

Abstract: Systems and methods are provided for generating an augmented reality display for users of augmented reality devices. Features provided in the AR displays may be used to update a non-augmented reality display. In addition, interactions in the AR displays may also be incorporated into the non-augmented reality display.

Abstract: Systems and methods provided for presenting supplemental content in an augmented reality environment where an object within a field of view of an augmented reality device of a user is identified and processed to detect a reference related to a participant in an event. A user profile or user social network is searched to identify a message from the user about the participant. The message may be combined with the object in the augmented reality field of view.

Abstract: Systems and methods are presented herein for generating a new language understanding model, based on a user request. A user may input a root language and a locale into an application for generating a student language model. The application may generate the student language model and may identify a teacher language model related to the student language model. The application may compare data from the identified teacher language model to the student language model. The application may determine a subset of data from the teacher language model is not contained in the student language model. If the application determines at least a subset of data from the teacher language model is not in the student language model, the application may add at least the subset of data from the teacher language model to the student language model.

Abstract: Systems and methods are described for improved sharing of an experience between users. A first image captured using a first user device is received by control circuitry. A second image captured using a second user device is received by the control circuitry. Control circuitry determines a first set of elements of the first image. Control circuitry determines a second set of elements of the second image. Control circuitry determines whether at least one element of the first set of elements corresponds to at least one element of the second set of elements. Control circuitry determines that a transient element is present in the first set of elements and is not present in the second set of elements. Control circuitry generates for display the transient element on the second user device.

Abstract: Systems and methods are disclosed herein for a recommendations engine that generates content recommendations using a trained model that is personalized based on the information corresponding to content consumption. The disclosed techniques herein provide a trained model to provide content recommendations. The trained model may have been trained using a predefined set of training data agnostic of a particular user profile. A system receives information corresponding to content consumption. The system may associate the information corresponding to content consumption with a profile. The system generates a personalized model based on the information corresponding to content consumption and on the trained model. The personalized model may be associated with the user profile. The system generates the content recommendations using the personalized model. The system then causes to be provided the content recommendations.

Abstract: Systems and methods are provided for generating a customized media asset to incentivize a first user to subscribe to a subscription service. A first user provides their subscription access information to a media provider. In response to receiving the subscription access information, the media provider determines whether the subscription access information is from an account subscribed for a trial period. If the account is subscribed for the trial period, the media provider presents a plurality of media assets for selection to the first user, receives a selection of a media asset available from the subscription service, generates a customized media asset based on a media asset consumption profile of the first user, wherein the customized media asset includes a segment from an additional media asset different from the selected media asset, and presents to the first user the customized media asset instead of the selected media asset.

Abstract: Systems and methods are described for modifying the content of a media content item. A a media content item is displayed on user equipment. A user reaction to one or more portions of the media content item is determined. The content of the media content item is modified based on the user reaction to one or more portions of the media content item.

Abstract: Systems and methods are described to access a set of reattempt query pairs, where each respective pair comprises an initial query and a reattempt of the initial query, and is associated with an indication of whether a reply generated for output based on the respective query pair was acceptable. In response to determining that a second query received after a first query constitutes a reattempt of the first query, a query pair in the set of reattempt query pairs may be identified that matches at least one of the first query and the second query, and is associated with an indication that a reply generated for output based on the query pair was acceptable. A search may be performed based on the identified query pair in the set of reattempt query pairs, and a reply may be generated for output based on the performed search.

Abstract: Systems and methods for improving audio playback at a playback device are described herein. In some embodiments, a system transitions between causing playback of a radio broadcast stream to causing playback of device music, such as in response to determining that a quality of the radio broadcast stream is below a threshold value. In some embodiments, a system selects songs to play based on device preferences of a plurality of different media devices. In some embodiments, a system selects a device from which to retrieve songs for playback based on one or more rules.