Singing Voice Separation with Deep U-Net Convolutional Networks
The decomposition of a music audio signal into its vocal and backing track components is analogous to image-toimage translation, where a mixed spectrogram is transformed into its constituent sources. We propose a novel application of the U-Net architecture — initially developed for medical imaging — for the task of source separation, given its proven capacity for recreating the fine, low-level detail required for high-quality audio reproduction. Through both quantitative evaluation and subjective assessment, experiments demonstrate that the proposed algorithm achieves state-of-the-art performance.
PDF AbstractCode
Tasks
Datasets
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Speech Separation | iKala | U-Net | NSDR | 11.094 (Vocal); 14.435 (Instrumental) | # 1 |
