Audio processing apparatus and method for audio scene classification

An audio processing method for classifying an audio signal into one or more audio scene classes, the audio signal comprising a component signal, wherein the method comprises:

• classifying the component signal in a classification as one of a foreground layer component signal or a background layer component signal;
• obtaining audio signal features on a basis of the audio signal;
• selecting one of a first set of weights or a second set of weights based on the classification of the component signal;
• and
• classifying the audio signal on a basis of an audio signal feature, the foreground layer component signal or background layer component signal, and the selected one of the first set of weights or the second set of weights.

A computer program product comprising a non-transitory computer readable medium program code for performing a method, wherein the method comprises:

• classifying a component signal in a classification as one of a foreground layer component signal or a background layer component signal;
• obtaining audio signal features on a basis of an audio signal;
• selecting one of a first set of weights or a second set of weights based on the classification of the component signal;
• and
• classifying the audio signal on a basis of an audio signal feature, the foreground layer component signal or background layer component signal, and the selected one of the first set of weights or the second set of weights.