APPARATUS AND METHOD FOR GENERATING AN AUDIO SIGNAL

An apparatus comprises a first receiver (201) that receives a sequence of real-time images of depth and/or visual data from an image sensor. A second receiver (209) receives a set of audio objects and metadata indicative of a relationship between the audio objects and material characteristics. An image generator (203) generates a sequence of output images comprising image objects corresponding to virtual scene objects in a real-world scene, and a detector (205) detects interactions between the virtual scene objects and real-world scene objects. An estimator (207) determines a material property of the real-world scene object in response to image data of a sequence of image frames, and a selector (211) selects an audio object in response to the material property and a material characteristic associated to the set of audio objects. An output circuit (213) generates the output audio signal comprising the first audio object. 一种装置包括从图像传感器接收深度和/或视觉数据的实时图像序列的第一接收器(201)。第二接收器(209)接收一组音频对象和指示音频对象与材料特性之间的联系的元数据。图像生成器(20