Autonomous Systems for Sound Integration and GeneratioN (ASSIGN)

在沉浸式媒体和游戏声音设计中，最大的挑战是寻找声音来源并将其与时间轴和视觉内容相结合。我们提出了一种智能决策系统，该系统从其他传感器数据中生成声音（具有沉浸式上下文）。“声音集成和生成的自主系统”（ASSIGN）项目利用创新的基于视觉的物体识别技术来控制声音合成技术，因此捕获的视频信息可以驱动声音的生成、放置和透视。这与视觉效果和电脑游戏相似，电脑游戏的渲染是由高级信息驱动的，例如，如果一个人掉了一个杯子，我们就会在游戏、电影或增强现实的虚拟世界中看到它掉下来。动画是对象的属性，声音效果也应该遵循同样的模式。它的商业潜力是巨大的，因为ASSIGN可以彻底改变声音设计过程。产出将包括一个自动音效生成的原型，以及市场分析、商业模式和推出商业服务的路线图。

In immersive media and game sound design, the biggest challenge is the effort required to source the sounds and integrate them with the timeline and visual content. We propose an intelligent decision-making system in a system that generates sounds (with their immersive context) from other sensor data. The Autonomous Systems for Sound Integration and GeneratioN (ASSIGN) project exploits innovative vision-based object recognition technologies to control sound synthesis techniques, so that captured video information can drive sound generation, placement and perspective. This parallels visual effects and computer games, where rendering is driven by high level information, e.g., if a man drops a glass, we see it falling in the virtual world of the game, film or augmented reality. The animation is a property of the object, and sound effects should follow this same paradigm. The business potential is compelling, since ASSIGN could revolutionise the sound design process. Outputs will include a prototype for autonomous sound effect generation, with market analysis, business models and road map to launch a commercial service.