Feature Learning for Chord Recognition: The Deep Chroma Extractor
This work addresses chord recognition for music analysis, presenting an incremental improvement by replacing hand-crafted features with learned ones.
The paper tackles the problem of noisy chroma features in chord recognition by proposing a learned chroma extractor using neural networks, which achieves superior performance compared to hand-crafted features on various datasets.
We explore frame-level audio feature learning for chord recognition using artificial neural networks. We present the argument that chroma vectors potentially hold enough information to model harmonic content of audio for chord recognition, but that standard chroma extractors compute too noisy features. This leads us to propose a learned chroma feature extractor based on artificial neural networks. It is trained to compute chroma features that encode harmonic information important for chord recognition, while being robust to irrelevant interferences. We achieve this by feeding the network an audio spectrum with context instead of a single frame as input. This way, the network can learn to selectively compensate noise and resolve harmonic ambiguities. We compare the resulting features to hand-crafted ones by using a simple linear frame-wise classifier for chord recognition on various data sets. The results show that the learned feature extractor produces superior chroma vectors for chord recognition.