@conference{7c6a059efb0945609f482f64ee045c7c,
author = "T. Barker and T. Virtanen",
abstract = "This paper details the use of a semi-supervised approach to audio source separation. Where only a single source model is available, the model for an unknown source must be estimated. A mixture signal is separated through factorisation of a feature-tensor representation, based on the modulation spectrogram. Harmonically related components tend to modulate in a similar fashion, and this redundancy of patterns can be isolated. This feature representation requires fewer parameters than spectrally based methods and so minimises overfitting. Following the tensor factorisation, the separated signals are reconstructed by learning appropriate Wiener-filter spectral parameters which have been constrained by activation parameters learned in the first stage. Strong results were obtained for two-speaker mixtures where source separation performance exceeded those used as benchmarks. Specifically, the proposed semi-supervised method outperformed both semi-supervised non-negative matrix factorisation and blind non-negative modulation spectrum tensor factorisation.",
booktitle = "Neural Networks (IJCNN), 2014 International Joint Conference on",
doi = "10.1109/IJCNN.2014.6889522",
isbn = "978-1-4799-1484-5",
keywords = "Wiener filters; audio signal processing; matrix decomposition; signal reconstruction; source separation; speech processing; tensors; Wiener-filter spectral parameters; activation parameters; audio source separation; blind nonnegative modulation spectrum te",
month = "7",
pages = "3556--3561",
title = "{S}emi-supervised non-negative tensor factorisation of modulation spectrograms for monaural speech separation",
year = "2014",
}