Computer Analysis of Audio and Music

点击翻译按钮获取中文摘要

The central focus of this proposal is the development of algorithms and tools to analyze sound with specific emphasis on music. The first theme is the exploration of deep learning techniques, a family of learning algorithms that are currently showing a lot of promise, for dynamic, multi-task, semi-supervised learning in the context of music analysis. The second theme is the development of better frameworks and programming language abstractions for representing time and probabilities in the development of multi-modal interactive systems. The third theme explore the use of music information retrieval techniques in the area of computer-assisted music pedagogy. The findings of this research have the potential to have significant impact in the rapidly expanding use of computer music technology.