Summary of Perceivers: a Multi-scale Perceiver with Effective Segmentation For Long-term Expressive Symbolic Music Generation, by Yungang Yi et al.
PerceiverS: A Multi-Scale Perceiver with Effective Segmentation for Long-Term Expressive Symbolic Music Generation
by Yungang Yi, Weihua Li, Matthew Kuo, Quan Bai
First submitted to arxiv on: 13 Nov 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Multimedia (cs.MM); 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 A novel architecture, PerceiverS, is proposed for symbolic music generation that addresses the challenge of creating both long-structured and expressive music. The model leverages Effective Segmentation and Multi-Scale attention mechanisms to learn long-term structural dependencies and short-term expressive details simultaneously. By combining cross-attention and self-attention in a Multi-Scale setting, PerceiverS captures long-range musical structure while preserving musical diversity. The model is evaluated using the Maestro dataset and demonstrates improvements in generating music of conventional length with expressive nuances. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new way to create music that’s both long-lasting and full of feeling has been developed. The system uses special techniques to learn about music structures and details at the same time, allowing it to generate music that’s both meaningful and interesting. This approach is tested using a large collection of musical pieces and shows significant improvements in creating music with the right length and emotional impact. |
Keywords
» Artificial intelligence » Attention » Cross attention » Self attention
