arXiv (Cornell University) · 2019 · 25 citations · 17 references
ComputingMusicologyAcousticsComputational AcousticsPhoneticsDeep LearningSpeech RecognitionVoice ProcessingLarge Margin Metric LearningSpeech Segregation
Singing Voice Separation (SVS) tries to separate singing voice from a given mixed musical signal. Recently, many U-Net-based models have been proposed for the SVS task, but there were no existing works that evaluate and compare various types of intermediate blocks that can be used in the U-Net architecture. In this paper, we introduce a variety of intermediate spectrogram transformation blocks. We implement U-nets based on these blocks and train them on complex-valued spectrograms to consider both magnitude and phase. These networks are then compared on the SDR metric. When using a particular block composed of convolutional and fully-connected layers, it achieves state-of-the-art SDR on the MUSDB singing voice separation task by a large margin of 0.9 dB. Our code and models are available online.
17
Densely Connected Convolutional Networks
Gao Huang, Zhuang Liu, Laurens van der Maaten et al. · 2017 · 44.7K citations
Deep Sparse Rectifier Neural Networks
Xavier Glorot, Antoine Bordes, Yoshua Bengio · 2012 · 5.4K citations