@inproceedings{624e4dff1a75457d9520b01f556c68ae,
title = "Unsupervised Deep Clustering for Source Separation: Direct Learning from Mixtures Using Spatial Information",
abstract = "We present a monophonic source separation system that is trained by only observing mixtures with no ground truth separation information. We use a deep clustering approach which trains on multichannel mixtures and learns to project spectrogram bins to source clusters that correlate with various spatial features. We show that using such a training process we can obtain separation performance that is as good as making use of ground truth separation information. Once trained, this system is capable of performing sound separation on monophonic inputs, despite having learned how to do so using multi-channel recordings.",
keywords = "Deep clustering, source separation, unsupervised learning",
author = "Efthymios Tzinis and Shrikant Venkataramani and Paris Smaragdis",
note = "Funding Information: Code: github.com/etzinis/unsupervised spatial dc Supported by NSF grant #1453104 Publisher Copyright: {\textcopyright} 2019 IEEE.; 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 ; Conference date: 12-05-2019 Through 17-05-2019",
year = "2019",
month = may,
doi = "10.1109/ICASSP.2019.8683201",
language = "English (US)",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "81--85",
booktitle = "2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings",
address = "United States",
}