Problem
Research questions and friction points this paper is trying to address.
Lempel-Ziv
music synthesis
over-copy
under-copy
Copying Versus Randomization in Lempel-Ziv Music Synthesis
🤖 AI Summary
本文利用Lempel-Ziv通用压缩算法生成音乐音符，通过调整字典中平均序列长度来控制算法对训练数据的过复制或欠复制问题。
📝 Abstract
We utilize Lempel-Ziv universal compression for music note generation. We control the algorithm's tendency to over-copy or under-copy training data by manipulating the average sequence length saved in the dictionary.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Lempel-Ziv
music synthesis
sequence length
dictionary manipulation
🔎 Similar Papers
No similar papers found.
