Unsupervised Interpretable Representation Learning For Singing Voice Separation

Abstract

In this work, we present a method for learning interpretable music signal representations directly from waveform signals. Our method can be trained using unsupervised objectives and relies on the denoising auto-encoder model that uses a simple sinusoidal model as decoding functions to reconstruct the singing voice. To demonstrate the benefits of our method, we employ the obtained representations to the task of informed singing voice separation via binary masking, and measure the obtained separation quality by means of scale-invariant signal to distortion ratio. Our findings suggest that our method is capable of learning meaningful representations for singing voice separation, while preserving conveniences of the the short-time Fourier transform like non-negativity, smoothness, and reconstruction subject to time-frequency masking, that are desired in audio and music source separation.

Stats

• citations5
• S2 citations—
• github stars0
• HF likes0
• heat score5.84
• arxiv keymimilakis2020unsupervised

Related papers

• Revisiting Representation Learning For Singing Voice Separation With Sinkhorn Distances (2020)0.00
• A Recurrent Encoder-decoder Approach With Skip-filtering Connections For Monaural Singing Voice Separation (2017)9.41
• Informed Group-sparse Representation For Singing Voice Separation (2018)7.16
• Monaural Singing Voice Separation With Skip-filtering Connections And Recurrent Inference Of Time-frequency Mask (2017)10.07
• Singing Voice Separation Using A Deep Convolutional Neural Network Trained By Ideal Binary Mask And Cross Entropy (2018)11.19
• Hierarchical Disentangled Representation Learning For Singing Voice Conversion (2021)6.34
• Depthwise Separable Convolutions Versus Recurrent Neural Networks For Monaural Singing Voice Separation (2020)0.00
• Unsupervised Singing Voice Conversion (2019)11.19