Abstract | ||
---|---|---|
Chord labels for recorded audio are in high demand both as an end product used by musicologists and hobby musi- cians and as an input feature for music similarity applica- tions. Many past algorithms for chord labelling are based on chromagrams, but distribution of energy in chroma frames is not well understood. Furthermore, non-chord notes com- plicate chord estimation. We present a new approach which uses as a basis a relatively simple chroma model to represent short-time sonorities derived from melody range and bass range chromagrams. A chord is then modelled as a mix- ture of these sonorities, or subchords. We prove the prac- ticability of the model by implementing a hidden Markov model (HMM) for chord labelling, in which we use the dis- crete subchord features as observations. We model gamma- distributed chord durations by duplicate states in the HMM, a technique that had not been applied to chord labelling. We test the algorithm by five-fold cross-validation on a set of 175 hand-labelled songs performed by the Beatles. Accu- racy figures compare very well with other state of the art approaches. We include accuracy specified by chord type as well as a measure of temporal coherence. |
Year | Venue | Keywords |
---|---|---|
2008 | ISMIR 2013 | cross validation,gamma distribution,hidden markov model,mixture model |
Field | DocType | Citations |
Pattern recognition,Computer science,Coherence (physics),Speech recognition,Artificial intelligence,Labelling,Hidden Markov model,Chord (music),Mixture model | Conference | 7 |
PageRank | References | Authors |
0.77 | 11 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Matthias Mauch | 1 | 381 | 26.97 |
Simon Dixon | 2 | 1164 | 107.57 |