• Corpus ID: 18774190

Four Timely Insights on Automatic Chord Estimation

@inproceedings{Humphrey2015FourTI,
  title={Four Timely Insights on Automatic Chord Estimation},
  author={Eric J. Humphrey and Juan Pablo Bello},
  booktitle={ISMIR},
  year={2015}
}
Automatic chord estimation (ACE) is a hallmark research topic in content-based music informatics, but like many other tasks, system performance appears to be converging to yet another glass ceiling. Looking toward trends in other machine perception domains, one might conclude that complex, data-driven methods have the potential to significantly advance the state of the art. Two recent efforts did exactly this for large-vocabulary ACE, but despite arguably achieving some of the highest results… 

Figures and Tables from this paper

Using Musical Relationships Between Chord Labels in Automatic Chord Extraction Tasks
TLDR
This paper analyzes the interdependence of the representations of chords and their associated distances, the precision of the chord alphabets, and the impact of the reduction of the alphabet before or after training of the model to improve the learning of statistical ACE models.
Structured Training for Large-Vocabulary Chord Recognition
TLDR
A deep convolutional-recurrent model for automatic chord recognition over a vocabulary of 170 classes is developed, trained to produce both the time-varying chord label sequence as well as binary encodings of chord roots and qualities.
Learning, Probability and Logic: Toward a Unified Approach for Content-Based Music Information Retrieval
TLDR
This perspective paper critically looks at the problem of automatic chord estimation from audio recordings as a case study of content-based algorithms, and advocates that the identified hurdles of current approaches could be overcome by recent developments in the area of Statistical Relational Artificial Intelligence (StarAI) that unifies probability, logic and (deep) learning.
Attend to Chords: Improving Harmonic Analysis of Symbolic Music Using Transformer-Based Models
TLDR
Experiments on conventional ACR and advanced functional harmony recognition indicate that the HT has the potential to surpass the BTC, especially in terms of chord segmentation quality, and an improved model is proposed.
Large-vocabulary Chord Transcription Via Chord Structure Decomposition
TLDR
A new model for audio chord recognition under a huge chord vocabulary, to decompose any chord label into a set of musically meaningful components, each with a much smaller vocabulary compared to the size of the overall chord vocabulary is proposed.
DECIBEL: Improving Audio Chord Estimation for Popular Music by Alignment and Integration of Crowd-Sourced Symbolic Representations
TLDR
DECIBEL is proposed, a new ACE system that exploits widely available MIDI and tab representations to improve ACE from audio only and shows that the integration of musical knowledge from heterogeneous symbolic music representations is a suitable strategy for addressing challenging MIR tasks such as ACE.
Beyond chord vocabularies: Exploiting pitch-relationships in a chord estimation metric
TLDR
An accuracy metric for chord estimation that compares the pitch content of the estimated chords against the ground truth that captures both the correct notes that are estimated and additional notes that is inserted into the estimate is presented.
A Hybrid Gaussian-HMM-Deep Learning Approach for Automatic Chord Estimation with Very Large Vocabulary
TLDR
This work proposes a hybrid Gaussian-HMM-Deep-Learning approach for automatic chord estimation with very large chord vocabulary, which has obvious advantage over the state-of-the-art large-vocabulary-with-inversions supportable ACE system in terms of large vocabularies, although is outperformed by in small vocABularies.
Transcribing Lead Sheet-Like Chord Progressions of Jazz Recordings
TLDR
A computational system that transcribes chords from jazz recordings, addressing the specific challenges they present and considering their inherent musical aspects, and allowing the creation of a lead sheet–like representation that is easy to interpret by both researchers and musicians is presented.
Local Key Estimation in Music Recordings: A Case Study Across Songs, Versions, and Annotators
TLDR
A cross-annotator study of Schubert's song cycle Winterreise annotated by three different music theory experts reveals that a substantial part of the systems’ errors coincides with annotator disagreement and can be traced back to musically explainable relationships among different keys.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 17 REFERENCES
An Expert Ground Truth Set for Audio Chord Recognition and Music Analysis
TLDR
Working with a team of trained jazz musicians, time-aligned transcriptions of the harmony in more than a thousand songs selected randomly from the Billboard “Hot 100” chart in the United States between 1958 and 1991 are collected.
Evaluating automatically estimated chord sequences
  • J. Pauwels, G. Peeters
  • Computer Science
    2013 IEEE International Conference on Acoustics, Speech and Signal Processing
  • 2013
TLDR
This paper presents a rigorous scheme to describe evaluation methods in a sound, unambiguous way that extends previous work specifically to take into account the large variance in chord estimation vocabularies and to perform evaluations on select sets of chords.
On the Relative Importance of Individual Components of Chord Recognition Systems
  • Taemin Cho, J. Bello
  • Computer Science
    IEEE/ACM Transactions on Audio, Speech, and Language Processing
  • 2014
TLDR
In this study, it is found that filtering has a significant impact on performance, but providing musical context information in the transition matrix is rendered moot by the need to enforce continuity in the estimations.
Exploring common variations in state of the art chord recognition systems
TLDR
It is found that filtering has a significant impact on performance, with self-transition penalties being the most important parameter; and that the benefits of using complex models are mostly, but not entirely, offset by an appropriate choice of filtering strategies.
Understanding Effects of Subjectivity in Measuring Chord Estimation Accuracy
TLDR
The extent of the confounding effect of subjectivity in reference annotations is investigated and it is shown that this effect is important, and they affect different types of automatic chord estimation systems in different ways.
Rethinking Automatic Chord Recognition with Convolutional Neural Networks
TLDR
This work adopts a different perspective of the problem, where several seconds of pitch spectra are classified directly by a convolutional neural network, and achieves state of the art performance through this initial effort to chord recognition.
A corpus analysis of rock harmony
TLDR
A corpus analysis of rock harmony using Rolling Stone magazine's list of the ‘500 Greatest Songs of All Time’ took the 20 top-ranked songs from each decade, creating a set of 100 songs, and showed that IV is the most common chord after I and is especially common preceding the tonic.
Symbolic Representation of Musical Chords: A Proposed Syntax for Text Annotations
TLDR
This paper defines a rigid, contextindependent syntax for representing chord symbols in text, supported with a new database of annotations using this system, and proposes a text represention for musical chord symbols that is simple and intuitive for musically trained individuals to write and understand.
Towards Timbre-Invariant Audio Features for Harmony-Based Music
TLDR
A novel procedure is described that further enhances chroma features by significantly boosting the degree of timbre invariance without degrading the features' discriminative power, revealing the musical meaning of certain pitch-frequency cepstral coefficients.
Audio Chord Recognition with Recurrent Neural Networks
TLDR
An efficient algorithm to search for the global mode of the output distribution while taking long-term dependencies into account is devised and the resulting method is competitive with state-of-the-art approaches on the MIREX dataset in the major/minor prediction task.
...
1
2
...