Abstract
A method is proposed that extracts a structural representation of percussive audio in an unsupervised manner. It consists of two parts: 1) The input signal is segmented into blocks of approximately even duration, aligned to a metrical grid, using onset and timbre feature extraction, agglomerative single-linkage clustering, metrical regularity calculation and beat detection. 2) The approx. equal length blocks are clustered into k clusters and the resulting cluster sequence is modelled by transition probabilities between clusters. The Hierarchical Dirichlet Process Hidden Markov Model is employed to jointly estimate the optimal number of sound clusters, to cluster the blocks, and to estimate the transition probabilities between clusters. The result is a segmentation of the input into a sequence of symbols (typically corresponding to hits of hi-hat, snare, bass, cymbal, etc.) that can be evaluated using the Adjusted Random Index (ARI). As a proof-of-concept, the system segmentation has been tested using two simple Disco-style drum loops, yielding a an ARI of 56% for the best stable HDP-HMM parameter setting.
Original language | English |
---|---|
Title of host publication | MML 2016 9th International Workshop on Machine Learning and Music : Held in Conjunction with the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD 2016) |
Editors | Rafael Ramirez, Darrell Conklin, José Manuel Iñesta |
Publication date | 2016 |
Pages | 6-10 |
Publication status | Published - 2016 |
Event | European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases: 9th International Workshop on Machine Learning and Music - Riva del Garda, Riva del Garda, Italy Duration: 19 Sept 2016 → 23 Sept 2016 http://ecmlpkdd2016.org/ |
Conference
Conference | European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases |
---|---|
Location | Riva del Garda |
Country/Territory | Italy |
City | Riva del Garda |
Period | 19/09/2016 → 23/09/2016 |
Internet address |
Keywords
- unsupervised learning
- Hierarchical Dirichlet Process
- Hidden Markov Model
- musical structure
- clustering