Скачать с ютуб LTI Colloquium: Towards General and Flexible Audio Source Separation в хорошем качестве

LTI Colloquium: Towards General and Flexible Audio Source Separation

Presented by Jonathan Le Roux (MERL) on December 9, 2022. Abstract: With the advent of deep-learning-based methods, audio source separation has seen a resurgence of interest and success. I will give an overview of techniques developed at MERL towards the goal of robustly and flexibly decomposing and analyzing an acoustic scene. In particular, I will describe our efforts to extend our early speech separation and enhancement methods to more challenging environments, and to more general and less supervised scenarios.