Rethinking Automatic Chord Recognition with Convolutional Neural Networks

Humphrey, Eric J.; Bello, Juan Pablo

doi:10.1109/icmla.2012.220

Cited by 81 publications

(56 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Typical hand-designed methods rely on folding multiple octaves of a spectral representation into a 12-semitone chromagram [13], smoothing in time, and matching against predefined chord templates. Humphrey and Bello [80] note the resemblance to the operations of a CNN, and demonstrate good performance with a CNN trained on constant-Q, linear-magnitude spectrograms preprocessed with contrast normalization and augmented with pitch shifting. Modern systems integrate temporal modelling, and extend the set of distinguishable chords.…”

Section: Applicationsmentioning

confidence: 98%

Deep Learning for Audio Signal Processing

Purwins

Virtanen

et al. 2019

IEEE J. Sel. Top. Signal Process.

604

247

View full text Add to dashboard Cite

Given the recent surge in developments of deep learning, this article provides a review of the state-of-the-art deep learning techniques for audio signal processing. Speech, music, and environmental sound processing are considered sideby-side, in order to point out similarities and differences between the domains, highlighting general methods, problems, key references, and potential for cross-fertilization between areas. The dominant feature representations (in particular, log-mel spectra and raw waveform) and deep learning models are reviewed, including convolutional neural networks, variants of the long short-term memory architecture, as well as more audio-specific neural network models. Subsequently, prominent deep learning application areas are covered, i.e. audio recognition (automatic speech recognition, music information retrieval, environmental sound detection, localization and tracking) and synthesis and transformation (source separation, audio enhancement, generative models for speech, sound, and music synthesis). Finally, key issues and future questions regarding deep learning applied to audio signal processing are identified.

show abstract

Section: Applicationsmentioning

confidence: 98%

Deep Learning for Audio Signal Processing

Purwins

Virtanen

et al. 2019

IEEE J. Sel. Top. Signal Process.

604

247

View full text Add to dashboard Cite

show abstract

“…It has been reported that ConvNet has outperformed previous state-of-the-art approaches for various MIR tasks such as onset detection [22], automatic chord recognition [23], [24], and music structure/boundary analysis [25], [26].…”

Section: Proliferation Of Deep Neural Network Inmentioning

confidence: 99%

Deep Convolutional Neural Networks for Predominant Instrument Recognition in Polyphonic Music

Han

Kim

Lee

2017

IEEE/ACM Trans. Audio Speech Lang. Process.

165

View full text Add to dashboard Cite

Abstract-Identifying musical instruments in polyphonic music recordings is a challenging but important problem in the field of music information retrieval. It enables music search by instrument, helps recognize musical genres, or can make music transcription easier and more accurate. In this paper, we present a convolutional neural network framework for predominant instrument recognition in real-world polyphonic music. We train our network from fixed-length music excerpts with a single-labeled predominant instrument and estimate an arbitrary number of predominant instruments from an audio signal with a variable length. To obtain the audio-excerpt-wise result, we aggregate multiple outputs from sliding windows over the test audio. In doing so, we investigated two different aggregation methods: one takes the average for each instrument and the other takes the instrument-wise sum followed by normalization. In addition, we conducted extensive experiments on several important factors that affect the performance, including analysis window size, identification threshold, and activation functions for neural networks to find the optimal set of parameters. Using a dataset of 10k audio excerpts from 11 instruments for evaluation, we found that convolutional neural networks are more robust than conventional methods that exploit spectral features and source separation with support vector machines. Experimental results showed that the proposed convolutional network architecture obtained an F1 measure of 0.602 for micro and 0.503 for macro, respectively, achieving 19.6% and 16.4% in performance improvement compared with other state-of-the-art algorithms.

show abstract

“…Up to now, CNN has found applications in speech recognition [18]- [19], music information retrieval [20], and median-filtering detection [21]. In this work, we will build a CNN-based network for more effective learning to recognize the subtle difference between the two types of audios.…”

Section: Proposed Network Architecturementioning

confidence: 99%

Audio Recapture Detection With Convolutional Neural Networks

Lin

Liu

Kang

2016

IEEE Trans. Multimedia

View full text Add to dashboard Cite

In this work, we investigate how features can be effectively learned by deep neural networks for audio forensic problems. By providing a preliminary feature preprocessing based on Electric Network Frequency (ENF) analysis, we propose a convolutional neural network (CNN) for training and classification of genuine and recaptured audio recordings. Hierarchical representations which contain levels of details of the ENF components are learned from the deep neural networks and can be used for further classification. The proposed method works for small audio clips of 2 seconds' duration, whereas the state of the art may fail with such small audio clips. Experimental results demonstrate that the proposed network yields high detection accuracy with each ENF harmonic component represented as a single-channel input. The performance can be further improved by a combined input representation which incorporates both the fundamental ENF and its harmonics. Convergence property of the network and the effect of using analysis window with various sizes are also studied. Performance comparison against the support tensor machine demonstrates the advantage of using CNN for the task of audio recapture detection. Moreover, visualization of the intermediate feature maps provides some insight into what the deep neural networks actually learn and how they make decisions.Index Terms-Electric network frequency, convolutional neural network, audio recapture detection.

show abstract

Rethinking Automatic Chord Recognition with Convolutional Neural Networks

Cited by 81 publications

References 5 publications

Deep Learning for Audio Signal Processing

Deep Learning for Audio Signal Processing

Deep Convolutional Neural Networks for Predominant Instrument Recognition in Polyphonic Music

Audio Recapture Detection With Convolutional Neural Networks

Contact Info

Product

Resources

About