Abstract: A method for classifying audio data. For a given piece of audio data a location or position for the given audio data within a mood space is generated and compared to a comparison mood space location. As a result of the comparison, comparison data are generated and provided as a classification result with respect to the given audio data.

Abstract: A method for mood detection, comprising receiving audio data, determining a mood for the audio data based on at least one mood model, receiving user feedback of a user for the determined mood, the user feedback being on a gradual scale and indicative as to whether the determined mood corresponds to a perceived mood of the user for the audio data, and adapting the mood model based on the user feedback.

Abstract: A method for classifying music includes providing music classification data, providing an unclassified piece of music to be classified, and deriving for each music class within the music classification data a respective Gish distance value. A finite set of a finite number of Gish distance values is descriptive for the relation of the unclassified piece of music to be classified with respect to a discrete and finite set of a finite number of music classes. Alternatively, for a given piece of music to be classified, music classification data of a n-tuple of at least three numbers are obtained, which are representative for the mood of the piece of music. From the n-tuple of numbers of the music classification data a pair of two dimensional coordinate values are determined, which are representative for the mood of the piece of music.

Abstract: A method for classifying audio data. For a given piece of audio data a location or position for the given audio data within a mood space is generated and compared to a comparison mood space location. As a result of the comparison, comparison data are generated and provided as a classification result with respect to the given audio data.

Abstract: A method for classifying music includes providing music classification data, providing an unclassified piece of music to be classified, and deriving for each music class within the music classification data a respective Gish distance value. A finite set of a finite number of Gish distance values is descriptive for the relation of the unclassified piece of music to be classified with respect to a discrete and finite set of a finite number of music classes. Alternatively, for a given piece of music to be classified, music classification data of a n-tuple of at least three numbers are obtained, which are representative for the mood of the piece of music. From the n-tuple of numbers of the music classification data a pair of two dimensional coordinate values are determined, which are representative for the mood of the piece of music.

Abstract: A Method for mood detection is proposed, comprising: receiving audio data (1), determining a mood (3) for said audio data (1) based on at least one mood model (8-1, 8-2, 8-3), receiving user feedback (F) of a user for said determined mood (3), said user feedback being indicative as to whether said determined mood (3) corresponds to a perceived mood of said user for said audio data (1), and adapting said mood model (8-1, 8-2, 8-3) based on said user feedback.