学术前沿｜音乐人工智能与音乐信息科技系系列讲座——重拾人工智能中的创造力
更新时间：2025-12-09 23:31 浏览量：1
主讲嘉宾：Philippe Esling 副教授
主持人：李小兵教授
时间：2025年12月17日18:00-19:30
重拾人工智能中的创造力：二、创作中的人工智能实用工具包
讲座简介
在过去的两年里，人工智能工具的爆炸式发展为创意实践领域同时带来了兴奋与忧虑。尤其是文本生成类工具，似乎已触及我们日常生活的所有潜在方面。然而，我们认为在音乐这一特定领域，这种方式是有误导性的，且有机会错失人工智能工具可能引发的真正变革，因为音乐中真正的发现存在于语言所无法触及的空间。另一方面，由ACIDS团队主导的研究项目旨在通过扩展深度生成概率学习模型，确保其对音乐合成过程的理解与感知，并提供创造性控制与交互方式，从而打造新一代音乐创作工具。在此背景下，我们尝试将深度人工智能模型应用于创意材料，旨在发展人工创造性智能。团队已开发出多款创新型乐器原型（如RAVE、AFTER、FlowSynth），并与知名作曲家（Bjork, Alexander Schubert, Pierce Warnecke）合作创作了多部音乐作品。今年，我们带来了令人振奋的新进展，在音乐创作、软件开发与科学研究三个前沿方向均投入了大量精力。
Over the past two years, the explosion of AI tools has both sparked excitement and fear for the creative practices. Especially, the text-to- family of tools seem to have reached every potential aspects of our daily life. However, we argue that in the specific realm of music, this objective is misled and can only miss the true revolution that can be generated by AI tools, since true discovery in music lies in a space that eludes language. In that separate direction, the research project led by the ACIDS collective aims to create the next-generation of musical instruments by extending deep generative probabilistic learning models to ensure their understanding and perception of musical synthesis, while providing creative controls and interactions. In this context, we experiment with deep AI models applied to creative materials, aiming to develop artificial creative intelligence. Our team has produced many prototypes of innovative instruments (RAVE, AFTER, FlowSynth) and musical pieces in collaborations with renowned composers (Bjork, Alexander Schubert, Pierce Warnecke). This year, we come back with some thrilling developments as we dedicated a lot of efforts on all three fronts of musical creation, software development and scientific research.
重拾人工智能中的创造力：一、机器学习的新视野
Reclaiming creativity from AI: （1）New visions on machine learning
摘要：本讲座将围绕机器学习模型的现状及现代研究的前沿方向，展开理论分析与观点阐述。同时，借此机会介绍ACIDS团队最新推出的系列工具。
Abstract: We will start by a theoretical analysis and point of view surrounding the current state of machine learning models and what are the current avenues in modern research. This will also allow us to introduce the latest tools proposed by the ACIDS collective.
重拾人工智能中的创造力：二、创作中的人工智能实用工具包
Reclaiming creativity from AI: （2）Practical toolkits for AI in creation
摘要：本讲座将探讨当前模型如何在创意工作流中实际部署与应用。重点深入讲解如何基于自有数据集训练模型，并剖析数据收集中需关注的共性特征与常见陷阱。
Abstract: We will discuss how the current models can be practically implemented and use in a creative workflow. Especially, we will provide a deep understanding of how we can train models on our own datasets and what are the common properties and pitfalls to look for when collecting data.
嘉宾简介
菲利普·艾斯林（Philippe Esling）于2007年获数学与计算机科学学士学位，2009年获声学与信号处理硕士学位，2012年获数据挖掘与机器学习博士学位。2012年，他在日内瓦大学遗传与进化系从事博士后研究。自2013年起，他受聘为法国声学与音乐研究所（IRCAM）及索邦大学终身副教授。在此短暂时间内，他已在国际权威期刊上发表超过20篇同行评议论文。2011年因其音频检索研究获青年学者奖，2013年因多目标时间序列数据挖掘研究获博士学位论文奖，2014年起多次获最佳论文奖。在应用研究领域，他主导开发并发布了首款计算机辅助配器软件Orchids（于2014年秋季上市），该软件已吸引全球数千名用户，并被多位知名作曲家运用于在国际舞台演出的音乐作品创作。他是机器学习在音乐生成与配器领域应用的首席研究员，并领导IRCAM新近成立的人工智能创作与数据科学（ACIDS）研究组。
Philippe Esling received a B.Sc in mathematics and computer science in 2007, a M.Sc in acoustics and signal processing in 2009 and a PhD on data mining and machine learning in 2012. He was a post-doctoral fellow in the department of Genetics and Evolution at the University of Geneva in 2012. He is now an associate professor with tenure at Ircam laboratory and Sorbonne Université since 2013. In this short time span, he authored and co-authored over 20 peer-reviewed journal papers in prestigious journals. He received a young researcher award for his work in audio querying in 2011, a PhD award for his work in multiobjective time series data mining in 2013 and several best paper awards since 2014. In applied research, he developed and released the first computer-aided orchestration software called Orchids, commercialized in fall 2014, which already has a worldwide community of thousands users and led to musical pieces from renowned composers played at international venues. He is the lead investigator of machine learning applied to music generation and orchestration, and lead the recently created Artificial Creative Intelligence and Data Science (ACIDS) group at IRCAM.
供稿：音乐人工智能与音乐信息科技系
设计：刘芯雅
团市委副书记王泰鹏调研我校共青团工作
“思政课堂实践优秀作品展演——乐声中的烽火岁月讲演会” 圆满举办