separation

Description

Publications

• MaD TwinNet: Masker-Denoiser Architecture with Twin Networks for Monaural Sound Source Separation
• Monaural Singing Voice Separation with Skip-Filtering Connections and Recurrent Inference of Time-Frequency Mask
• A Recurrent Encoder-Decoder Approach With Skip-Filtering Connections for Monaural Singing Voice Separation
• Non-Negative Factorisation Techniques for Sound Source Separation
• Binary Non-Negative Matrix Deconvolution for Audio Dictionary Learning
• Object-based Modeling of Audio for Coding and Source Separation
• Compositional Models for Audio Processing: Uncovering the structure of sound mixtures
• Audio Signal Modeling with Sinusoids Plus Noise