Conference Proceedings

A Unified Neural Architecture for Instrumental Audio Tasks

S Spratley, D Beck, T Cohn

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | IEEE | Published : 2019

Abstract

© 2019 IEEE. Within Music Information Retrieval (MIR), prominent tasks - including pitch-tracking, source-separation, super-resolution, and synthesis - typically call for specialised methods, despite their similarities. Conditional Generative Adversarial Networks (cGANs) have been shown to be highly versatile in learning general image-to-image translations, but have not yet been adapted across MIR. In this work, we present an end-to-end supervisable architecture to perform all aforementioned audio tasks, consisting of a WaveNet synthesiser conditioned on the output of a jointly-trained cGAN spectrogram translator. In doing so, we demonstrate the potential of such flexible techniques to unify..

View full abstract