Summary of Watermarking Training Data Of Music Generation Models, by Pascal Epple et al.
Watermarking Training Data of Music Generation Models
by Pascal Epple, Igor Shilov, Bozhidar Stevanoski, Yves-Alexandre de Montjoye
First submitted to arxiv on: 11 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Sound (cs.SD); Audio and Speech Processing (eess.AS)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper investigates whether audio watermarking techniques can be used to detect unauthorized usage of content for training music generation models. The authors compare outputs generated by a model trained on watermarked data with one trained on non-watermarked data, examining factors such as watermarking technique, proportion of watermarked samples in the training set, and robustness against the model’s tokenizer. Results show that imperceptible audio watermarking techniques can cause noticeable shifts in the model’s outputs, while also studying the robustness of a state-of-the-art watermarking technique to removal techniques. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper explores using audio watermarking techniques to detect when music generation models are trained on copyrighted material. It compares two types of generated music: one from a model trained on watermarked songs and another from a model trained on normal songs. The study looks at what makes the difference in these outputs and how well the watermarking technique can withstand attempts to remove it. |
Keywords
» Artificial intelligence » Tokenizer
