Deep neural networks for single channel source separation

Grais, Emad Mounir and Şen, Mehmet Umut and Erdoğan, Hakan (2014) Deep neural networks for single channel source separation. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014), Florence, Italy

Full text not available from this repository. (Request a copy)


In this paper, a novel approach for single channel source separation (SCSS) using a deep neural network (DNN) architecture is introduced. Unlike previous studies in which DNN and other classifiers were used for classifying time-frequency bins to obtain hard masks for each source, we use the DNN to classify estimated source spectra to check for their validity during separation. In the training stage, the training data for the source signals are used to train a DNN. In the separation stage, the trained DNN is utilized to aid in estimation of each source in the mixed signal. Single channel source separation problem is formulated as an energy minimization problem where each source spectra estimate is encouraged to fit the trained DNN model and the mixed signal spectrum is encouraged to be written as a weighted sum of the estimated source spectra. The proposed approach works regardless of the energy scale differences between the source signals in the training and separation stages. Nonnegative matrix factorization (NMF) is used to initialize the DNN estimate for each source. The experimental results show that using DNN initialized by NMF for source separation improves the quality of the separated signal compared with using NMF for source separation.
Item Type: Papers in Conference Proceedings
Uncontrolled Keywords: Single channel source separation; deep neural network; nonnegative matrix factorization
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Faculty of Engineering and Natural Sciences > Academic programs > Electronics
Faculty of Engineering and Natural Sciences
Depositing User: Hakan Erdoğan
Date Deposited: 21 Jan 2015 16:30
Last Modified: 26 Apr 2022 09:18

Actions (login required)

View Item
View Item