Abstract: An electronic device obtains a listening history for a media item, the listening history including retention information indicating, for each respective portion of a plurality of portions of the media item, a number of listeners who listened to the respective portion of the media item. The electronic device, using the retention information, determines a pattern indicating a reduction in the number of listeners who listened to corresponding portions of the media item and determines a start time and an end time corresponding to a first portion of the corresponding portions of the media item. In accordance with the determination that the first portion of the corresponding portions of the media item meets predefined sub-content criteria, the electronic device stores an indication that the first portion of the media item comprises first sub-content, different from primary content, embedded in the media item.

Abstract: An electronic device receives a first audio content item that includes a plurality of sound sources. The electronic device generates a representation of the first audio content item. The electronic device determines, from the representation of the first audio content item: a representation of an isolated sound source, and frequency data associated with the isolated sound source. Determining the representation of the isolated sound source and the frequency data associated with the isolated sound source includes using a neural network to jointly determine the representation of the isolated sound source and the frequency data associated with the isolated sound source. The electronic device determines that a portion of a second audio content item matches the first audio content item using the representation of the isolated sound source and/or the frequency data associated with the isolated sound source.

Abstract: A system, method and computer product for training a neural network system. The method comprises applying an audio signal to the neural network system, the audio signal including a vocal component and a non-vocal component. The method also comprises comparing an output of the neural network system to a target signal, and adjusting at least one parameter of the neural network system to reduce a result of the comparing, for training the neural network system to estimate one of the vocal component and the non-vocal component. In one example embodiment, the system comprises a U-Net architecture. After training, the system can estimate vocal or instrumental components of an audio signal, depending on which type of component the system is trained to estimate.

Abstract: An example system for playing media content with a media playback device in a vehicle can be programmed to obtain a sound measurement indicative of a sound level associated with playback of the media content by the media playback device in the vehicle. The example system also can determine a deviation in an expected sound level based upon the sound measurement. Finally, the system can modify playback of the media content by the media playback device (110) based upon the deviation.

Abstract: Methods, systems and computer program products are provided for content generation. A distribution of policies is defined based on an action space. Distribution parameters are received from a reinforcement learning (RL) algorithm. In turn, a policy is randomly sampled from the distribution of policies. A candidate content item is generated using the sampled policy. A quality of the candidate content item is measured based on a predefined quality criteria and a parameter model is adjusted as specified by the reinforcement learning algorithm to obtain a plurality of updated distribution parameters. Environment settings are passed to a trained parameter model to obtain a plurality of policy distribution parameters. A predetermined number of policies from the distribution of policies are then sampled and the plurality of environment settings are passed to the predetermined number of sampled policies to obtain at least one content item.

Abstract: A media content item recommendation system recommends media content items based on one or more attributes of a seed playlist. The recommended media content items can be determined from a plurality of existing playlists that have been created over a period of time. Such existing playlists can be selected based on similarity to the seed playlist.

Abstract: An adaptive multi-model item selection method, comprising: receiving, from one of a plurality of client devices, a request including a client-side feature vector representing a state of the client device; determining, by an advocate model, a probability distribution of a plurality of specialist cluster models from the client-side feature vector; choosing, by a use case selector, a cluster corresponding to a use case from the probability distribution; and obtaining, by the use case selector based on the cluster (i.e., the cluster that was sampled by the user case selector), a specialist cluster model from the plurality of specialist cluster models.

Abstract: An electronic device, for each media content item of a plurality of media content items, receives a respective score for each a first set of objectives and one or more other objectives and generates a respective score between a user and the media content item. The generating includes applying a first ordered weighted average to the respective scores for the first set of objectives, to produce a first combined score for the first set of objectives, applying a second ordered weighted average to the respective scores for a second set of objectives, wherein the second set of objectives includes (i) a resulting objective corresponding to the first set of objectives and having the first combined score and (ii) the one or more other objectives. The electronic device streams media content to the user selected based on the respective scores between the user and the media content items.

Abstract: A cuepoint determination system utilizes a convolutional neural network (CNN) to determine cuepoint placements within media content items to facilitate smooth transitions between them. For example, audio content from a media content item is normalized to a plurality of beats, the beats are partitioned into temporal sections, and acoustic feature groups are extracted from each beat in one or more of the temporal sections. The acoustic feature groups include at least downbeat confidence, position in bar, peak loudness, timbre and pitch. The extracted acoustic feature groups for each beat are provided as input to the CNN on a per temporal section basis to predict whether a beat immediately following the temporal section within the media content item is a candidate for cuepoint placement. A cuepoint placement is then determined from among the candidate cuepoint placements predicted by the CNN.

Abstract: Systems, devices, apparatuses, components, methods, and techniques for generating and playing a selectable content depth media program are provided. Media content items are edited to produce selectable depth media segments which are assembled into selectable depth media programs. A media-playback device is configured to navigate and play the selectable depth media program through interaction by a listening user. The user selects the desired content depth for each media segment.

Abstract: Systems, methods, and devices for human-machine interfaces for utterance-based playlist selection are disclosed. In one method, a list of playlists is traversed and a portion of each is audibly output until a playlist command is received. Based on the playlist command, the traversing is stopped and a playlist is selected for playback. In examples, the list of playlists is modified based on a modification input.

Abstract: A system is provided for streaming media content in a vehicle. The system includes a personal media streaming appliance system configured to connect to a media delivery system and receive media content from the media delivery system at least via a cellular network. The personal media streaming appliance system operates to transmit a media signal representative to the received media content to a vehicle media playback system so that the vehicle media playback system operates to play the media content in the vehicle. Customized voice communications are generated based on receiving input, such as a user query and/or a media track change indication.

Abstract: A system, method and computer program product for accessing content. The method comprises processing at least one image with a classifier, and, in response to the at least one image being processed by the classifier, outputting from the classifier a value indicative of the likelihood that the at least one image belongs to at least one classification. The method also comprises determining whether the at least one image belongs to the at least one classification, based on the value, and accessing predetermined content when it is determined that the at least one image belongs to the at least one classification. Images may be classified by, e.g., genre, musical album, concept, or the like, and, in cases where an image belongs to any such classes, predetermined content (e.g., metadata and/or an audio track) relating thereto is identified and presented to the user.

Abstract: An example system is provided for playing media content with a media playback device in a vehicle The example system can obtain vehicle movement data indicative of movement of the vehicle and sound data indicative of sound in the vehicle. The example system can also determine that the vehicle movement data and the sound data are at a given level, and switch the media playback device to a low power consumption mode.

Abstract: A request to play a media content item is received. It is determined whether the play request is ambiguous. Responsive to determining that the play request is ambiguous, then it is determined whether to play a suspended media content item or an alternate media content item. The determination can be made based on a length of time that the suspended media content item has been suspended, a media content item type, or a state, among other factors. Responsive to the determination, playback of the suspended or alternate media content item is initiated.

Abstract: Methods, systems, and computer programs for generating a playlist of media content items that are popular with the friends of the first user. A first user taste profile is determined and a user taste profile is determined for each of a plurality of social connections. A similarity score is calculated between the first user taste profile and the user taste profile of each social connection. Media content items consumed by social connections with the highest similarity score are selected and placed in a playlist for the first user.

Abstract: A system for playing media content items operates to provide smooth transitions between the media content items to continuously support a user's repetitive motion activity. The system can generate crossfade data containing information for transitions between media content items. The mix-in and mix-out points for the transitions are calculated to eliminate one or more portions of media content items that have lower musical energy than a majority portion of the items, and to maintain substantially consistent and/or stable musical energy (e.g., audio power or sound power) throughout the media content items including transitions therebetween.

Abstract: Methods, systems and computer program products are provided personalizing recommendations of items with associated explanations. The example embodiments described herein use contextual bandits to personalize explainable recommendations (“recsplanations”) as treatments (“Bart”). Bart learns and predicts satisfaction (e.g., click-through rate, consumption probability) for any combination of item, explanation, and context and, through logging and contextual bandit retraining, can learn from its mistakes in an online setting.

Abstract: The present disclosure relates to the comparison of data items, such as media data items or streams, e.g. audio files or streams, to determine a similarity between the data items. A device receives a plurality, or ensemble, of data items, and calculates the pairwise similarity scores between a number of unique pairs of data items within the ensemble. For any given pair of data items, the pairwise similarity score is compared with an overall similarity score for an “indirect path” connecting the pair of data items via one or more intermediate data items. If the indirect path indicates a closer similarity between the data items, the pairwise score is updated based on the overall similarity score of the indirect path. The updated similarity score generated by this comparison then provides an improved indication of the similarity of the data items compared to the prior art method.

Abstract: Utterance-based user interfaces can include activation trigger processing techniques for detecting activation triggers and causing execution of certain commands associated with particular command pattern activation triggers without waiting for output from a separate speech processing engine. The activation trigger processing techniques can also detect speech analysis patterns and selectively activate a speech processing engine.