AILGFeb 9, 2018

Neural Dynamic Programming for Musical Self Similarity

arXiv:1802.03144v310 citations
Originality Incremental advance
AI Analysis

This is an incremental improvement for music analysis, addressing motif detection in symbolic music.

The authors tackled the problem of detecting repeated motifs in symbolic music by developing a neural sequence model based on a learned edit distance mechanism, which outperformed a strong LSTM benchmark on real and synthetic data.

We present a neural sequence model designed specifically for symbolic music. The model is based on a learned edit distance mechanism which generalises a classic recursion from computer sci- ence, leading to a neural dynamic program. Re- peated motifs are detected by learning the transfor- mations between them. We represent the arising computational dependencies using a novel data structure, the edit tree; this perspective suggests natural approximations which afford the scaling up of our otherwise cubic time algorithm. We demonstrate our model on real and synthetic data; in all cases it out-performs a strong stacked long short-term memory benchmark.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes