AMT Seminar: Vesa Välimäki – Machine learning and digital audio effects скачать в хорошем качестве

AMT Seminar: Vesa Välimäki – Machine learning and digital audio effects

AMT Seminars: http://www.musica.ed.ac.uk Speaker: Vesa Välimäki (Aalto University, Finland) Title: Machine learning and digital audio effects Date: October 2024 More details at: https://www.musica.ed.ac.uk/archive/2... Abstract: Many new audio effects processing methods employ machine learning techniques, but this was not the case just five years ago. This talk discusses the developments that led to the paradigm shift in our research field, which followed a few years behind some closely related fields, such as speech recognition and synthesis. It has been a nice surprise that machine learning can better solve many audio processing problems than previous signal-processing methods. However, there are also counterexamples for which we have not found a perfect machine-learning-based solution. Audio time-scale modification is a problem for which ideal training data is unavailable, and the current best method is based on traditional signal processing. Generative machine learning, such as diffusion models, can provide excellent solutions to problems that seemed almost impossible earlier, such as the reconstruction of long gaps, or audio inpainting.