← authors · overview

• D3Net: Densely connected multidilated DenseNet for music source separation
  2020 · 48 citations
• SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization
  2022 · 13 citations
• Improving DNN-based Music Source Separation using Phase Features
  2018 · 12 citations
• Hierarchical disentangled representation learning for singing voice conversion
  2021 · 8 citations
• MMDenseLSTM: An efficient combination of convolutional and recurrent neural networks for audio source separation
  2018 · 6 citations
• Recursive speech separation for unknown number of speakers
  2019 · 6 citations
• Training Speech Enhancement Systems with Noisy Speech Datasets
  2021 · 6 citations
• Hierarchical Diffusion Models for Singing Voice Neural Vocoder
  2022 · 4 citations
• Robust One-Shot Singing Voice Conversion