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: Audio mix information is received from a plurality of users. Mix rules are determined from the audio mix information from the plurality of users, wherein the mix rules include a first mix rule associated with a first audio item. The first mix rule relates to an overlap of the first audio item with another audio item. The first mix rule is made available to one or more clients. After making the first mix rule available, an indication, from a respective client device, that the first audio item is to be mixed with a second audio item at the respective client device in accordance with the first mix rule is received. In response to the indication, a specification of the first mix rule is transmitted to the respective client device to be applied by the respective client device to generate a transition between the first audio item and the second item.

Abstract: Methods, systems, and related products that provide emotion-sensitive responses to user's commands and other utterances received at an utterance-based user interface. Acknowledgements of user's utterances are adapted to the user and/or the user device, and emotions detected in the user's utterance that have been mapped from one or more emotion features extracted from the utterance. In some examples, extraction of a user's changing emotion during a sequence of interactions is used to generate a response to a user's uttered command. In some examples, emotion processing and command processing of natural utterances are performed asynchronously.

Abstract: A server system accesses a listening history of a user of the media-providing service, where the user is in a demographic group. For each track of a plurality of tracks in the listening history of the user, the server system determines a year associated with the track and calculates a first metric based at least in part of an affinity of members of a demographic group, as compared to members of other demographic groups, of music from the year associated with the track. The server system selects content for the user based on the first metric and provides the selected content to a client device associated with the user.

Abstract: Systems, devices, apparatuses, components, methods, and techniques for automatically generating media previews are provided. An example media system for automatically generating media previews for a particular artist include a trailer generation application configured to receive input specifying an artist and duration of a trailer, automatically select clips from two or more media items by the artist, and automatically arrange and combine the clips into a media trailer for later playback.

Abstract: Systems, devices, apparatuses, components, methods, and techniques for saving media content to a context for later playback are provided. An example media-playback device for identifying and playing media content for a user traveling in a vehicle includes a context detecting device, a context-driven playback engine, and a media playback engine. Contexts are established by parameters that can be detected by a media-playback device. Contexts are situations that are defined by one or more locations, times, events, activities, people, and devices. Media content is saved to the contexts for later playback. The contexts are detected by the context detecting device, the associated media content is identified by the context-driven playback engine, and the media content is automatically played through the media playback engine, without additional input required by 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: Methods, systems and computer program products are provided for generating a playlist. An application programming interface (API) receives a request to generate a playlist, where the request includes a set of rule-primitives. A playlist engine evaluator evaluates a rule corresponding to each rule-primitive in the set of rule-primitives across a catalog of media content, calculates a cost associated with each item in the catalog of media content, and generates a playlist based on the items of the catalog having the lowest costs.

Abstract: Methods and a computer-readable storage device are disclosed for generating a frequency representation of a query audio file. The frequency representation represents information about at least a number of frequencies within a time range containing a number of time frames of the audio content information and a level associated with each of said frequencies. At least one of area of data points in the frequency representation is selected. A fingerprint for each selected area of data points is generated by applying a trained neural network onto said selected area of data points thereby generating a vector in a metric space. A distance between at least one of the generated query fingerprints and at least one reference fingerprint is calculated using a specified distance metric. A reference audio file having associated reference fingerprints which have produced at least one associated distance satisfying a predetermined threshold is identified.

Abstract: A system and methods for acquiring cadence and selecting a song version based on the acquired cadence are disclosed. If the system detects a new cadence, then a new song version that corresponds to the new cadence can be played. The new song version playback can start in a corresponding position as the location of playback in a currently-playing song version. Each related song version shares one or more characteristics, such as melody, but is different in at least one characteristic, such as tempo.

Abstract: A skip behavior analyzer is part of a media delivery system that allows for unbiased A/B testing of a plurality of versions of a song. The media delivery system stores a plurality of versions of a song and randomly selects, for each requesting device, a version of the song to associate with that device. Each time the device requests the song, thereafter, the media delivery system will provide the same version of the song for consistency. The media delivery system then gathers song play and skip information, calculates the differences in distribution of the skip behavior, and provides the skip information to allow a music composer to better determine which version of a song is more popular and why that is so.

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: An audio cancellation system includes a voice enabled computing system that is connected to an audio output device using a wired or wireless communication network. The voice enabled computing device can provide media content to a user and receive a voice command from the user. The connection between the voice enabled computing system and the audio output device introduces a time delay between the media content being generated at the voice enabled computing device and the media content being reproduced at the audio output device. The system operates to determine a calibration value adapted for the voice enabled computing system and the audio output device. The system uses the calibration value to filter the user's voice command from a recording of ambient sound including the media content, without requiring significant use of memory and computing resources.

Abstract: Systems, devices, apparatuses, components, methods, and techniques for media content playback during travel are provided. An example method of generating a user interface for a media playback device. The method includes the step of displaying a first user interface screen in a first display format. The first display format including graphical representations of a plurality of selectable controls. The method also includes the step of determining that the media playback device is travelling and after determining that the media playback device is travelling, converting the first user interface screen to a second display format. The second display format includes fewer graphical representations of the plurality of selectable controls than the first display format.

Abstract: In one aspect, a client device receives a request to stream a media item from a first position. Content corresponding to the media item includes samples identified in a container file. The client device obtains, independently of the container file, a seektable that is not included with the container file and that identifies a plurality of segments into which content corresponding to the media item is divided. The seektable is stored using a mark-up language that is natively compatible with a software development kit (SDK) executing on the client device. The client device consults the seektable to determine a segment of the media item to retrieve in response to the request, the segment including content at the first position, and, after consulting the seektable, retrieves the segment of the media item and plays the content corresponding to the first position using the retrieved segment.

Abstract: A server receives a request to play a selected playlist from a first electronic device associated with a host listener. The playlist includes audio items having a common attribute. The server also receives an identity of a guest listener having a second electronic device and retrieves an indication of taste of the guest listener based on the received identity. The server selects an additional audio item based at least in part on the indication of taste of the guest listener and the common attribute of the audio items of the selected playlist, and incorporates the additional audio item into the selected playlist.

Abstract: A method for controlling media presentation is disclosed. In some implementations, the method is performed at a first electronic device having one or more processors and memory storing one or more programs for execution by the one or more processors. The first electronic device displays a webpage including a control element, such as a “play” button. The webpage originates from a webpage server. The first electronic device receives a user input, such as a mouse click, selecting the control element. In response to the user input, the first electronic device sends a media control request to a media server. The media control request is configured to cause the media server to control presentation of first media content at a second electronic device associated with the user, wherein the second electronic device is different from the first electronic device, and wherein the media server is different from the webpage server.

Abstract: A server system that provides a content service determines a preference of a first user of the content service for a first media item. The preference has a magnitude and is either positive or negative. The server system provides the first media item for playback based on a request from an application that is executing on a mobile electronic device of the first user with an audio jack and a speaker. The server system receives data indicating that playback of the first media item by the mobile electronic device is through the speaker and modifies the magnitude of the preference, which includes increasing the magnitude of the preference based on the received data. The server system generates a media recommendation for the first user in accordance with the modified preference and provides the media recommendation to the mobile electronic device.

Abstract: A system, method and computer product for estimating a component of a provided audio signal. The method comprises converting the provided audio signal to an image, processing the image with a neural network trained to estimate one of vocal content and instrumental content, and storing a spectral mask output from the neural network as a result of the image being processed by the neural network. The neural network is a U-Net. The method also comprises providing the spectral mask to a client media playback device, which applies the spectral mask to a spectrogram of the provided audio signal, to provide a masked spectrogram. The media playback device also transforms the masked spectrogram to an audio signal, and plays back that audio signal via an output user interface.

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.