A Large-Scale Study of Language Models for Chord Prediction
Korzeniowski, Filip, Sears, David R. W., Widmer, Gerhard
We conduct a large-scale study of language models for chord prediction. Specifically, we compare N-gram models to various flavours of recurrent neural networks on a comprehensive dataset comprising all publicly available datasets of annotated chords known to us. This large amount of data allows us to systematically explore hyper-parameter settings for the recurrent neural networks---a crucial step in achieving good results with this model class. Our results show not only a quantitative difference between the models, but also a qualitative one: in contrast to static N-gram models, certain RNN configurations adapt to the songs at test time. This finding constitutes a further step towards the development of chord recognition systems that are more aware of local musical context than what was previously possible.
Apr-5-2018
- Country:
- South America > Brazil
- North America
- United States
- Texas (0.04)
- Florida > Palm Beach County
- Boca Raton (0.04)
- Canada > Alberta
- United States
- Europe
- Germany (0.04)
- Spain (0.04)
- Netherlands > Utrecht (0.04)
- United Kingdom > England
- Greater London > London (0.04)
- Portugal > Porto
- Porto (0.04)
- France > Île-de-France
- Austria > Upper Austria
- Linz (0.04)
- Asia
- Genre:
- Research Report > New Finding (0.87)
- Industry:
- Media > Music (1.00)
- Leisure & Entertainment (1.00)
- Technology: