Starting in winter semester 2026/27, the AudioLabs offer a new lecture that covers selected DL-based approaches for audio signals, with emphasis on modern generative models. Further topics include diffusion-based music synthesis, nonnegative autoencoders for audio decomposition, and differentiable alignment methods. The course focuses on generally applicable methods and offers a critical perspective on their potential and limitations. CME students can take the lecture as a Technical Elective and earn 2.5 ECTS.
Selected Topics in Deep Learning for Audio, Speech, and Music Processing
