1. MedleyDB: A multitrack dataset for annotation-intensive MIR research,2014
2. A consolidated view of loss functions for supervised deep learningbased speech enhancement,2020
3. Learning with instance-dependent label noise: A sample sieve approach;arXiv preprint arXiv:2010.02347,2020
4. Investigating U-Nets with various intermediate blocks for spectrogram-based singing voice separation,2020
5. Hybrid spectrogram and waveform source separation,2021