Abstract: Audio advertisements for music services can be created and played to minimize any perceived discontinuity by a listener from a preceding song. Specifically, a voice-over content item (e.g., a spoken advertisement produced without music) may combined with a non-song musical content item (e.g., backing music specifically produced for advertisements) to create an audio advertisement to be played after a song on a streaming music service. The non-song musical content item may be selected based on its similarity to the preceding song (e.g., genre, tempo, or harmony) and/or a musical preference of a user (e.g., a preferred genre obtained through a user's music service account and/or selected by the user). The genre of both the preceding song and a musical preference of a user may be used to select a non-song musical content item genre by a weighting that determines the probability of the genre used for an advertisement.

Abstract: Audio advertisements for music services can be created and played to minimize any perceived discontinuity by a listener from a preceding song. Specifically, a voice-over content item (e.g., a spoken advertisement produced without music) may combined with a non-song musical content item (e.g., backing music specifically produced for advertisements) to create an audio advertisement to be played after a song on a streaming music service. The non-song musical content item may be selected based on its similarity to the preceding song (e.g., genre, tempo, or harmony) and/or a musical preference of a user (e.g., a preferred genre obtained through a user's music service account and/or selected by the user). The genre of both the preceding song and a musical preference of a user may be used to select a non-song musical content item genre by a weighting that determines the probability of the genre used for an advertisement.

Abstract: A system with a decision engine having logic for using metadata for one or more song recordings and one or more non-song musical content items. The logic performs the steps of: interpreting the metadata for the first song recording; identifying a first non-song musical content item for playback at or near an end of the first song recording based on a similarity between the first song recording and the first non-song musical content item; and, in response to determining that the first song recording is at or near its end of playback, forming an altered playback of the first non-song musical content item by performing via real time digital audio signal processing an alteration of the first non-song musical content item to be rhythmically continuous in terms of tempo to the first song recording and/or harmonically continuous in terms of key and/or mode to the first song recording.

Abstract: A system with a decision engine having logic for using metadata for one or more song recordings and one or more non-song musical content items. The logic performs the steps of: interpreting the metadata for the first song recording; identifying a first non-song musical content item for playback at or near an end of the first song recording based on a similarity between the first song recording and the first non-song musical content item; and, in response to determining that the first song recording is at or near its end of playback, forming an altered playback of the first non-song musical content item by performing via real time digital audio signal processing an alteration of the first non-song musical content item to be rhythmically continuous in terms of tempo to the first song recording and/or harmonically continuous in terms of key and/or mode to the first song recording.

Abstract: A system, computer program product and method for altering the playback of one or more song recordings is described herein. Embodiments of the system comprise a decision engine having logic for using metadata for the one or more song recordings. The logic performs the steps of interpreting the metadata to identify a plurality of bar/beat locations for the one or more song recordings; responsive to playback of at least one of the song recordings, determining whether the song recording is playing at one of the bar/beat locations; and in response to determining that the song recording is playing at one of the bar/beat locations, forming the altered playback by performing via real time digital audio signal processing at least one of: altering a segue between song recordings, altering a form of at least one of the song recordings, and altering an instrumentation of at least one of the song recordings.