学术前沿∣音乐人工智能系系列讲座——“智能音频制作”

发布时间: 2022-06-14 10:09:38 浏览次数 : 253 来源:中央音乐学院

主讲嘉宾：JOSH REISS教授

主持人：李小兵教授

时间：2022年6月13日20:00-21:30

题目：智能音频制作

主办：音乐人工智能与音乐信息科技系

入场方式

ZOOM会议号：978 438 6825

入会密码：8888

Title:

Intelligent Audio Production

智能音频制作

Abstract:

In music, films, games and virtual reality, we recreate the sounds around us, or create unreal sounds to evoke emotions and capture the imagination. But there is a world of fascinating phenomena related to sound and perception that is not yet understood. If we can gain a deep understanding of how we perceive and respond to complex audio, we could produce new content of unprecedented quality and range.

This talk is targeted at a general audience, and considers the possibilities opened up by such research. What are the limits of human hearing? Could a robot replace the sound engineer? Can we create a realistic virtual world without relying on recorded samples? If every sound in a major film or game soundtrack were computer-generated, could we reach a level of realism comparable to modern computer graphics? Investigating such questions as the potential to revolutionize sound design and music production.

在音乐、电影、游戏和虚拟现实中，我们通过再现周围的声音或创造虚构的声音，来激发情感，捕捉想象。然而，关于声音和感知，还存在着许多奇妙迷人却尚未被人类理解的现象。如果我们能够深入地了解我们感知和响应复杂音频的机制，我们就能制作出质量和广度都前所未有的新内容。本次演讲将面向大众介绍此类研究潜在的发展方向——人类听力的极限是什么?机器人能代替音响工程师吗?我们可以不依赖录音采样来创造贴近现实的虚拟声音世界吗?如果电影或游戏配乐中的每一个声音都是计算机生成的，那么在真实感上，我们能达到与现代计算机图形学相当的水平吗?以上这些课题，都能够为声音设计和音乐制作带来革命性的转变。

Biography:

Josh Reiss is the current President of the Audio Engineering Society (AES). He is a Professor with the Centre for Digital Music at Queen Mary University of London. His primary focus of research is on the use of state-of-the-art signal processing techniques for sound design and audio production. He has published more than 200 scientific papers, He is the author of Working with the Web Audio API and co-author of Intelligent Music Production, and the textbook Audio Effects: Theory, Implementation and Application.

Josh Reiss现任音频工程学会(AES)主席，伦敦玛丽女王大学数字音乐中心教授。他的主要研究重点是将最先进的信号处理技术运用在声音设计和音频制作中。曾发表200余篇科学论文，是Working with the Web Audio API的开发者，也是《智能音乐制作》(Intelligent Music Production)和《音频效果：理论、实现和应用》(Audio Effects: Theory, Implementation and Application)教材的合著者。