Feature Learning for Chord Recognition: The Deep Chroma Extractor
arXiv:1612.05065
Abstract
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.
In Proceedings of the 17th International Society for Music Information Retrieval Conference (ISMIR), New York, USA, 2016
Cited by in corpus (10)
- Deep Learning for Audio Signal Processing
- A Fully Convolutional Deep Auditory Model for Musical Chord Recognition
- A Tutorial on Deep Learning for Music Information Retrieval
- Using musical relationships between chord labels in automatic chord extraction tasks
- Genre-Agnostic Key Classification With Convolutional Neural Networks
- Improved Chord Recognition by Combining Duration and Harmonic Language Models
- DLR : Toward a deep learned rhythmic representation for music content analysis
- Lead Sheet Generation and Arrangement by Conditional Generative Adversarial Network
- A Hybrid Approach to Audio-to-Score Alignment
- Automatic Chord Recognition with Higher-Order Harmonic Language Modelling