用词向量方法将音符序列转为音高，效果接近真实音高。
From melodic note sequences to pitches using word2vec
- 把音符当词语，用word2vec建模旋律上下文
- 2维语义空间中预测音高，相关系数达0.80
- 适合音乐生成与旋律分析研究者参考
将常用于语言建模的word2vec技术应用于旋律，将音符视为句子中的词语，以捕捉音高信息。本研究使用两个数据集：20首儿童歌曲和巴赫奏鸣曲片段。语义空间维度极小，仅为2维。基于前2、3或4个音符建立上下文，进行音符预测。多变量分析显示，表示音符的语义向量与实际音高的多重相关系数约为0.80。
原文摘要 · Abstract (English)
Applying the word2vec technique, commonly used in language modeling, to melodies, where notes are treated as words in sentences, enables the capture of pitch information. This study examines two datasets: 20 children's songs and an excerpt from a Bach sonata. The semantic space for defining the embeddings is of very small dimension, specifically 2. Notes are predicted based on the 2, 3 or 4 preceding notes that establish the context. A multivariate analysis of the results shows that the semantic vectors representing the notes have a multiple correlation coefficient of approximately 0.80 with their pitches.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。