A Large-Scale Study of Language Models for Chord Prediction
This work addresses chord prediction for music analysis, but it is incremental as it builds on existing methods with systematic hyper-parameter exploration.
The study compared N-gram models to recurrent neural networks for chord prediction using a large dataset, finding that certain RNN configurations adapt to songs at test time, offering a qualitative improvement over static models.
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.