TY - GEN
T1 - End-To-End Non-Negative Autoencoders for Sound Source Separation
AU - Venkataramani, Shrikant
AU - Tzinis, Efthymios
AU - Smaragdis, Paris
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/5
Y1 - 2020/5
N2 - Discriminative models for source separation have recently been shown to produce impressive results. However, when operating on sources outside of the training set, these models can not perform as well and are cumbersome to update. Classical methods like Nonnegative Matrix Factorization (NMF) provide modular approaches to source separation that can be easily updated to adapt to new mixture scenarios. In this paper, we generalize NMF to develop end-to-end non-negative auto-encoders and demonstrate how they can be used for source separation. Our experiments indicate that these models deliver comparable separation performance to discriminative approaches, while retaining the modularity of NMF and the modeling flexibility of neural networks.
AB - Discriminative models for source separation have recently been shown to produce impressive results. However, when operating on sources outside of the training set, these models can not perform as well and are cumbersome to update. Classical methods like Nonnegative Matrix Factorization (NMF) provide modular approaches to source separation that can be easily updated to adapt to new mixture scenarios. In this paper, we generalize NMF to develop end-to-end non-negative auto-encoders and demonstrate how they can be used for source separation. Our experiments indicate that these models deliver comparable separation performance to discriminative approaches, while retaining the modularity of NMF and the modeling flexibility of neural networks.
KW - Non-negative autoencoder
KW - deep learning
KW - end-to-end
KW - non-negative matrix factorization
KW - single-channel audio separation
KW - source separation
UR - http://www.scopus.com/inward/record.url?scp=85089221191&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85089221191&partnerID=8YFLogxK
U2 - 10.1109/ICASSP40776.2020.9053588
DO - 10.1109/ICASSP40776.2020.9053588
M3 - Conference contribution
AN - SCOPUS:85089221191
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 116
EP - 120
BT - 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020
Y2 - 4 May 2020 through 8 May 2020
ER -