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: 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: 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 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 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: 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.

Abstract: A full attention mechanism of a multilingual transformer model is converted into a Longformer attention mechanism to generate a Longformer multilingual transformer model. The Longformer multilingual transformer model is finetuned to perform a summarization task based on episode-description:episode-transcript pairs, thereby generating a finetuned Longformer multilingual transformer model. The Longformer multilingual transformer model also can further be finetuned to perform a summarization task based on article-summary:full-original-article pairs. A summary of a query episode transcript can be generated using the single-finetuned Longformer multilingual transformer model and/or the double-finetuned Longformer multilingual transformer model. The multilingual transformer-based model enables systems, methods and computer products to be capable of generating multilingual abstractive summaries.

Abstract: Systems and methods are provided for detecting wake words. An electronic device detects, from a microphone array, an audio signal in an environment proximate to the audio front end system. The electronic device processes the audio signal using a plurality of wake word detection engines, including dynamically adjusting how many wake word detection engines are available for processing the audio signal. The electronic device independently adjusts respective wake word detection thresholds for the plurality of wake word detection engines used to process the audio signal.

Abstract: A server system receives an indication of a media content item from a device and determines a first set of values that correspond to characteristics of the indicated media content item. The method further includes analyzing a defined set of media content items to identify a proxy content item. The identified proxy media content item has a second set of values that meets similarity criteria for the first set of values. The method includes generating, from the defined set of media content items, a result set of media content items that are associated with the proxy media content item. The method also includes determining a result set of users of the media content provider associated with the result set of media content items and transmitting, to the device of the user, information associated with the result set of users of the media content provider.

Abstract: A server system receives an indication of a media content item from a device and determines a first set of values that correspond to characteristics of the indicated content item. The server system analyzes a defined set of content items to identify a proxy media content item. The identified proxy media content item has a second set of values that meets similarity criteria for the first set of values. The server system determines, based on analysis of a plurality of sets of media content items, a result set of one or more media content items that are related to the proxy media content item. The server system provides information associated with the result set of media content items to the device of the user.

Abstract: An electronic device stores a plurality of vector representations for respective media content items in a vector space, where each vector represents a media content item. The electronic device receives a first set of input parameters representing a previous session of a user of the media-providing service where the previous session included two or more of the respective media content items. The electronic device then receives a second set of input parameters representing a current context of the user and provides the first set of input parameters and the second set of input parameters to a neural network to generate a prediction vector for a current session. The prediction vector is embedded in the vector space.

Abstract: Methods, systems and computer program products are provided for query understanding. A non-focused query quantifier generates non-focused query features that quantify a non-focused query and a non-focused query predictor generates a prediction associated with the non-focused query based on the non-focused query features.

Abstract: Media content playback is based on an identified geographic location of a sound source. A geolocation of a target venue is determined. A first geolocation of a media playback device is determined. An indication that the media playback device is within a threshold distance of the target venue is received. Media content associated with the target venue is transferred to the media playback device, wherein one or more characteristics of the media content are dynamically modified to simulate audio originating from the target device. The one or more characteristics of the media content can include audio content characteristics associated with a timing filter, a loudness filter, and a timbre filter.

Abstract: Systems and methods for audio advertising user interaction are disclosed. A voice interactive device causes an advertising audio file to be played for a user. The user can express interest in the advertising content of the advertising audio file by speaking one of a plurality of predetermined intents. Based on expressed user response, one or more results can be provided to the user and/or to a user device. The results relate to advertising content of the advertising audio file.

Abstract: A playlist preview is generated to provide a preview of media content items identified by a media playlist. The playlist preview can be created by selecting all or some of the media content items in the playlist, determining preview portions of the selected media content items, and arranging the preview portions with or without a transition effect. The playlist preview can be easily shared with other users through, for example, social media sites.

Abstract: At a client computer, a web browser is connected to a local web server. The local web server is coupled with a local utility executing on the client computer that is distinct from the web browser. The web browser sends, to the local web server via a first communications channel, a first open-ended message that does not require a return message. The local web server waits until the local utility determines there is information to be provided to the web browser and sends, via the first communications channel, a first return message responsive to the first open-ended message. The web browser, in response to and upon receiving the first return message responsive, maintains communication with the local web server by sending, using a second communications channel distinct from the first communications channel, a second open-ended message that does not require a return message to the local web server.

Abstract: A system for generating and distributing a digital mixtape. In one example, the system can receive a user command to generate a digital mixtape including a user-defined compilation of music. The user command identifies a recipient of the digital mixtape and identifies one or more media content items to be included in the music compilation for the recipient. The digital mixtape can also include audio recordings from the user to be added to the digital mixtape.