Apparatus and method for generating output signals by using audio object based metadata

Apparatus for generating at least one audio signal representing a superposition of at least two objects of different audio, comprising: a processor for processing an input signal audio purposes of providing a representation of objects of the signal audio input, wherein the at least two objects of different audio are separated from each other, the at least two objects of different audio are available as object signals separate audio, and the at least two objects of different audio are manipulatable independently; a manipulator of objects to manipulate the target signal or audio object signal of improved audio of at least one audio object based on object-based audio relating to at least one audio object metadata for obtaining a signal manipulated audio object signal or a manipulated mixed audio objects to the at least one audio object; and mixer objects, for mixing the object representation by combining the manipulated audio object with an object manipulated different audio differently from at least one audio object.