Search device and associated methods
A search device and associated methods use music emotions to browse, organize and retrieve music collections. The search device comprises a processor and an interface. The processor uses machine learning techniques to determine music emotion according to music features and organizes music by emotions for browsing and retrieving music collections. The interface connects to the processor and allows a person to retrieve desired music from the processor. Methods associated with the search device comprise a processor initialization method, a method of loading new music into the search device and several methods of retrieving desired music from the search device.
1. A retrieval method for a search device, comprising:
selecting a query method from a query-by-emotion-point (QBEP) method, a query-by-emotion-trajectory (QBET) method, a query-by-artist-emotion (QBAE) method and a query-by-emotion-region (QBER) method through an interface of the search device, wherein the QBAE method is a combination of the QBEP and a conventional artist-based retrieval method, and the QBEP method, the QBET method, the QBAE method and the QBER method are run on the search device;
receiving at least one pair of emotion coordinates of a specific music emotion in an emotion space by a user; and
retrieving at least one desired music based on the emotion coordinates using the query method,
wherein the search device comprises a processor configured to organize music by emotions in the emotion space for browsing and retrieving music collections, the emotion space is a 2-dimentional coordinate system and has an arousal axis and a valence axis, and each music is represented by a pair of emotion coordinates (R v , R a ) in the emotion space;
wherein when the QBEP query method is selected as the query method, the search device retrieves multiple pieces of the desired music corresponding to the specific music emotion by:
receiving a point of the desired music emotion; and
generating the emotion coordinates according to the point; and
retrieving the desired music corresponding to the emotion coordinates;
wherein when the QBET query method is selected as the query method, the search device retrieves multiple pieces of the desired music with specific song-by-song emotion variation by:
receiving a trajectory of desired music emotions from the platform and quantizing the trajectory to generate a series of emotion coordinates; and
receiving the series of emotion coordinates; and
retrieving a list of the desired music ordered in such a way that the song-by-song emotion variation in the music list is consistent with the emotion variation specified by the trajectory;
wherein when the QBAE query method is selected as the query method, the search device retrieves music collections of at least one artist corresponding to the specific music emotion by:
receiving the emotion coordinates;
retrieving music corresponding to the emotion coordinates; and
generating an artist list corresponding to the retrieved music; and
wherein when the QBER query method is selected as the query method, the search device retrieves multiple pieces of music in a region by:
receiving a region of desired music emotions and quantizing the region; and
retrieving a collection of music with emotion coordinates within the region and generating a music playlist of the music collection.