-
Wikitext-103 and MusDB datasets
The dataset used in the paper is not explicitly mentioned, but it is mentioned that the authors trained a 16 layers transformer (Vaswani et al., 2017) based language model on... -
Deep Transform: Cocktail Party Source Separation via Probabilistic Re-Synthesis
Monaural and binaural cocktail party listening scenarios with mixed speech signals and ground truth separated and re-synthesized audio. -
Martian time-series unraveled: A multi-scale nested approach with factorial v...
Unsupervised source separation involves unraveling an unknown set of source signals recorded through a mixing operator, with limited prior knowledge about the sources, and only...
