Evaluating automatically estimated chord sequences

Pauwels, Johan; Peeters, Geoffroy

doi:10.1109/icassp.2013.6637748

Cited by 19 publications

(11 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[9]), but this is not the focus of the current paper. Instead, our focus is on the observation that any evaluation metric, including the commonly used NHD, is valuable only if the reference annotations are 'correct.…”

Section: Introductionmentioning

confidence: 90%

“…Indeed, the likelihood function is given as: (9) If the consensuses are known, the experts' biases can be estimated efficiently using maximum likelihood estimation. On the other hand, given an estimate of the biases , the most probable label for data point can be estimated as (10) The EM algorithm starts with a random initialization of and iterates these two steps until convergence (possibly with several restarts).…”

Section: A Crowd Learningmentioning

confidence: 99%

See 1 more Smart Citation

Understanding Effects of Subjectivity in Measuring Chord Estimation Accuracy

McVicar

Santos-Rodríguez

et al. 2013

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

To assess the performance of an automatic chord estimation system, reference annotations are indispensable. However, owing to the complexity of music and the sometimes ambiguous harmonic structure of polyphonic music, chord annotations are inherently subjective, and as a result any derived accuracy estimates will be subjective as well. In this paper, we investigate the extent of the confounding effect of subjectivity in reference annotations. Our results show that this effect is important, and they affect different types of automatic chord estimation systems in different ways. Our results have implications for research on automatic chord estimation, but also on other fields that evaluate performance by comparing against human provided annotations that are confounded by subjectivity.

show abstract

Section: Introductionmentioning

confidence: 90%

Section: A Crowd Learningmentioning

confidence: 99%

Understanding Effects of Subjectivity in Measuring Chord Estimation Accuracy

McVicar

Santos-Rodríguez

et al. 2013

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…The proposed ACE algorithm has been evaluated using the same method proposed in [14] with the software MusOOEvaluator 4 and the pre-set called Mirex2010, on the same database. The Mirex2010 evaluation metric calculates a segment-based score by considering matches between overlapping segments of the estimated chord sequence and the annotated chord sequence.…”

Section: Discussionmentioning

confidence: 99%

Audio Chord estimation based on meter modeling and two-stage decoding

Degani

Dalai

Leonardi

et al. 2017

Proceedings of the 10th International Symposium on Image and Signal Processing and Analysis

View full text Add to dashboard Cite

In Music Information Retrieval (MIR) different approaches in modeling the meter structure of a song have been proposed and have been proved to be beneficial for the task of Audio Chord Estimation (ACE). In this paper we propose a novel approach that integrates the meter and beat information into the Hidden Markov Model (HMM) used for Audio Chord Estimation. In addition to the proposed meter model, we introduce also a modification in the inference procedure of the aforementioned Hidden Markov Model, in order to better capture the temporal correlation between chords progression. Experimental results show that the proposed approach is effective as the classical approaches in modeling the meter structure, but with a substantially reduced model complexity. Moreover, the proposed two-stage decoding procedure produces a significant improvement in the chords estimation accuracy.

show abstract

“…According to [50], chord symbol recall (CSR) is a suitable metric to evaluate chord estimation performance. Since 2013, MIREX has used CSR to estimate how well the predicted chords match the ground truth:…”

Section: Corpus and Evaluation Resultsmentioning

confidence: 99%

Chord Recognition Based on Temporal Correlation Support Vector Machine

2016

View full text Add to dashboard Cite

Abstract:In this paper, we propose a method called temporal correlation support vector machine (TCSVM) for automatic major-minor chord recognition in audio music. We first use robust principal component analysis to separate the singing voice from the music to reduce the influence of the singing voice and consider the temporal correlations of the chord features. Using robust principal component analysis, we expect the low-rank component of the spectrogram matrix to contain the musical accompaniment and the sparse component to contain the vocal signals. Then, we extract a new logarithmic pitch class profile (LPCP) feature called enhanced LPCP from the low-rank part. To exploit the temporal correlation among the LPCP features of chords, we propose an improved support vector machine algorithm called TCSVM. We perform this study using the MIREX'09 (Music Information Retrieval Evaluation eXchange) Audio Chord Estimation dataset. Furthermore, we conduct comprehensive experiments using different pitch class profile feature vectors to examine the performance of TCSVM. The results of our method are comparable to the state-of-the-art methods that entered the MIREX in 2013 and 2014 for the MIREX'09 Audio Chord Estimation task dataset.

show abstract

Evaluating automatically estimated chord sequences

Cited by 19 publications

References 6 publications

Understanding Effects of Subjectivity in Measuring Chord Estimation Accuracy

Understanding Effects of Subjectivity in Measuring Chord Estimation Accuracy

Audio Chord estimation based on meter modeling and two-stage decoding

Chord Recognition Based on Temporal Correlation Support Vector Machine

Contact Info

Product

Resources

About