@inproceedings{69489ab828964706a70ca3688091d833,
title = "A style transfer approach to source separation",
abstract = "Training neural networks for source separation involves presenting a mixture recording at the input of the network and updating network parameters in order to produce an output that resembles the clean source. Consequently, supervised source separation depends on the availability of paired mixture-clean training examples. In this paper, we interpret source separation as a style transfer problem. We present a variational auto-encoder network that exploits the commonality across the domain of mixtures and the domain of clean sounds and learns a shared latent representation across the two domains. Using these cycle-consistent variational auto-encoders, we learn a mapping from the mixture domain to the domain of clean sounds and perform source separation without explicitly supervising with paired training examples.",
keywords = "Style transfer, consistency loss, deep learning, domain translation, neural networks, source separation, unsupervised learning",
author = "Shrikant Venkataramani and Efthymios Tzinis and Paris Smaragdis",
note = "∗Supported by NSF grant #1453104; 2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2019 ; Conference date: 20-10-2019 Through 23-10-2019",
year = "2019",
month = oct,
doi = "10.1109/WASPAA.2019.8937203",
language = "English (US)",
series = "IEEE Workshop on Applications of Signal Processing to Audio and Acoustics",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "170--174",
booktitle = "2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2019",
address = "United States",
}