Rethinking Automatic Chord Recognition with Convolutional Neural Networks

By Eric J. Humphrey, Juan Pablo Bello. 2012

137 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Deep Learning: Methods and Applications (2014, background): “In the general field of audio and music processing, the impacted areas by deep learning include mainly music signal processing and music information retrieval [15, 22, 141, 177, 178, 179, 319].”
Automatic Tagging Using Deep Convolutional Neural Networks (2016, methodology): “CNNs have been applied to various audio analysis tasks, mostly assuming that auditory events can be detected or recognised by seeing their time-frequency representations.”
An End-to-End Neural Network for Polyphonic Piano Music Transcription (2015, methodology): “Although ConvNets have been applied to some problems in MIR [23], [24], they remain unexplored for transcription tasks.”
MidiNet: A Convolutional Generative Adversarial Network for Symbolic-Domain Music Generation (2017, background): “of reinforcement learning [19], we will also be interested in integrating to MidiNet more computational models dealing with different aspects of music information, such as automatic chord recognition [20], music auto-tagging [14], and music emotion recognition [21]. Such computational models can pro”
Audio Chord Recognition with Recurrent Neural Networks (2013, background): “Following recent advances in training deep neural networks [1] and its successful application to chord recognition [19], music annotation and auto-tagging [15], polyphonic music transcription [24] and speech recognition [17], we will exploit the power of deep architectures to extract features from t”
Crepe: A Convolutional Representation for Pitch Estimation (2018, result): “This contrasts with many other problems in music information retrieval like chord ID [16] and beat detection [17], where data-driven methods have been shown to consistently outperform heuristic approaches.”
Feature learning and deep architectures: new directions for music informatics (2013, methodology): “In an effort to account for this behavior, the work presented in Humphrey and Bello (2012) adopts a slightly different view of chord recognition.”
Deep Learning for Audio Signal Processing (2019, background): “Humphrey and Bello [80] note the resemblance to the”
Learning-Based Methods for Comparing Sequences, with Applications to Audio-to-MIDI Alignment and Matching (2016, methodology): “• Using 2× 1 pooling layers as in chapter 5 and (Humphrey and Bello, 2012); we found 2× 2 max-pooling worked better for embedding networks.”