Jointly Detecting and Separating Singing Voice: A Multi-Task Approach

@inproceedings{Stoller2018JointlyDA,
  title={Jointly Detecting and Separating Singing Voice: A Multi-Task Approach},
  author={D. Stoller and S. Ewert and S. Dixon},
  booktitle={LVA/ICA},
  year={2018}
}
A main challenge in applying deep learning to music processing is the availability of training data. One potential solution is Multi-task Learning, in which the model also learns to solve related auxiliary tasks on additional datasets to exploit their correlation. While intuitive in principle, it can be challenging to identify related tasks and construct the model to optimally share information between tasks. In this paper, we explore vocal activity detection as an additional task to stabilise… Expand
13 Citations
Multi-task Learning for Detection, Recovery, and Separation of Polyphonic Music
  • Highly Influenced
Interleaved Multitask Learning for Audio Source Separation with Independent Databases
  • 4
  • PDF
Joint Singing Pitch Estimation and Voice Separation Based on a Neural Harmonic Structure Renderer
  • 4
  • PDF
Evolutionary Multi-objective Training Set Selection of Data Instances and Augmentations for Vocal Detection
  • 1
  • PDF
Zero-mean Convolutional Network with Data Augmentation for Sound Level Invariant Singing Voice Separation
  • Kin Wah Edward Lin, M. Goto
  • Computer Science
  • ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2019
  • 1
  • PDF
A Streamlined Encoder/decoder Architecture for Melody Extraction
  • Tsung-Han Hsieh, Li Su, Y. Yang
  • Computer Science, Engineering
  • ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2019
  • 10
  • PDF
Singing voice separation using a deep convolutional neural network trained by ideal binary mask and cross entropy
  • 14
  • PDF
Weakly Informed Audio Source Separation
  • 6
  • Highly Influenced
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 21 REFERENCES
Deep clustering and conventional networks for music separation: Stronger together
  • 104
  • PDF
Adversarial Semi-Supervised Audio Source Separation Applied to Singing Voice Extraction
  • D. Stoller, S. Ewert, S. Dixon
  • Computer Science, Mathematics
  • 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2018
  • 44
  • PDF
Learning to Pinpoint Singing Voice from Weakly Labeled Examples
  • 52
  • PDF
Singing-Voice Separation from Monaural Recordings using Deep Recurrent Neural Networks
  • 106
  • PDF
A Joint Separation-Classification Model for Sound Event Detection of Weakly Labelled Data
  • 22
  • PDF
Structured dropout for weak label and multi-instance learning and its application to score-informed source separation
  • S. Ewert, M. Sandler
  • Computer Science, Mathematics
  • 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2017
  • 15
  • PDF
Singing Voice Separation with Deep U-Net Convolutional Networks
  • 217
  • Highly Influential
  • PDF
MedleyDB: A Multitrack Dataset for Annotation-Intensive MIR Research
  • 207
  • PDF
Singing voice analysis and editing based on mutually dependent F0 estimation and source separation
  • 35
  • PDF
Automatic music transcription: challenges and future directions
  • 240
  • PDF
...
1
2
3
...