Summary of From Melodic Note Sequences to Pitches Using Word2vec, by Daniel Defays
From melodic note sequences to pitches using word2vec
by Daniel Defays
First submitted to arxiv on: 29 Oct 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
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 The proposed approach applies word2vec technique to melodies by treating notes as words in sentences, enabling the capture of pitch information. By leveraging two datasets – 20 children’s songs and an excerpt from a Bach sonata – this study demonstrates how notes can be predicted based on the context established by preceding notes (up to 4). The semantic vectors representing the notes exhibit a strong correlation with their pitches, with a multiple correlation coefficient of approximately 0.80. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper uses a special technique called word2vec to understand music. Instead of words being letters and sentences, notes in melodies are treated as words and phrases. By using this approach, researchers can learn patterns in music that help predict what comes next. They tested this idea on two types of songs – children’s songs and a famous piece by Bach. The results show that the technique is very effective at predicting pitches based on what came before. |
Keywords
» Artificial intelligence » Word2vec
