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.

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.

Abstract: A computing device comprising a display screen, the computing device being configured to decompose a media recording into a plurality of media recording salient events, apply each of the media recording salient events to a reinforcement model, display on the display screen (i) a mapping of the plurality of media recording salient events and (ii) for at least one of the plurality of media recording salient events, at least one selectable next best action, the computing device further configured to replace at least one of the plurality of media recording salient events with at least one selectable next best action to create a derivative media recording including at least one replacement media recording action.

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 media-playback device acquires a heart rate, selects a song with a first tempo, and initiates playback of the song. The song meets a set of qualification criteria and the first tempo is based on the heart rate, such as being equal to or less than the heart rate. The media-playback device also initiates playback of a binaural beat at a first frequency. Over a period of time, the binaural beat's first frequency is changed to a second frequency. Over the period of time, the first tempo can also be changed to a second tempo, where the second tempo is slower than the first tempo.

Abstract: Audio translation system includes a feature extractor and a style transfer machine learning model. The feature extractor generates for each of a plurality of source voice files one or more source voice parameters encoded as a collection of source feature vectors, and generates for each of a plurality of target voice files one or more target voice parameters encoded as a collection of target feature vectors. The style transfer machine learning model trained on the collection of source feature vectors for the plurality of source voice files and the collection of target feature vectors for the plurality of target voice files to generate a style transformed feature vector.

Abstract: A system and method for confirming a voice command of a media playback device is disclosed. The method includes receiving an instruction of a voice command and producing an audio confirmation of the command. A confirmation may be playing a media context item associated with the command, playing a verbal confirmation phrase, or playing a non-verbal audio cue.

Abstract: Methods, systems, and related products that provide detection of media content items that are under-locatable by machine voice-driven retrieval of uttered requests for retrieval of the media items. For a given media item, a resolvability value and/or an utterance resolve frequency is calculated by a number of playbacks of the media item by a speech retrieval modality to a total number of playbacks of the media item regardless of retrieval modality. In some examples, the methods, systems and related products also provide for improvement in the locatability of an under-locatable media item by collecting and/or generating one or more pronunciation aliases for the under-locatable item.

Abstract: A text-to-speech engine creates audio output that includes synthesized speech and one or more media content item snippets. The input text is obtained and partitioned into text sets. A track having lyrics that match a part of one of the text sets is identified. The location of the track's audio that contains the lyric is extracted based on forced alignment data. The extracted audio is combined with synthesized speech corresponding to the remainder of the input text to form audio output.

Abstract: A method of determining relations between music items, the method comprising determining a first input representation for a symbolic representation of a first music item, mapping the first input representation onto to one or more subspaces derived from a vector space using a first model, wherein each subspace models a characteristic of the music items, determining a second input representation for music data representing a second music item, mapping the second input representation onto the one or more subspaces using a second model, determining a distance between the mappings of the first and second input representation in each subspace, wherein the distance represents the degree of relation between the first and second input representation with respect to the characteristic modelled by the subspace.