A Simple Method to Determine if a Music Information Retrieval System is a “Horse”
Open accessThe DOI matches its Crossref record.
Abstract
We propose and demonstrate a simple method to explain the figure of merit (FoM) of a music information retrieval (MIR) system evaluated in a dataset, specifically, whether the FoM comes from the system using characteristics confounded with the “ground truth” of the dataset. Akin to the controlled experiments designed to test the supposed mathematical ability of the famous horse “Clever Hans,” we perform two experiments to show how three state-of-the-art MIR systems produce excellent FoM in spite of not using musical knowledge. This provides avenues for improving MIR systems, as well as their evaluation. We make available a reproducible research package so that others can apply the same method to evaluating other MIR systems.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cited by
CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning
Johnson, J., Hariharan, B., van der Maaten, L., Fei-Fei, L., Zitnick, C. L., & Girshick, R. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.215 · Cited by 1,781
Arjovsky, M., Bottou, L., Gulrajani, I., & Lopez-Paz, D. (2019) · arXiv · doi:10.48550/arxiv.1907.02893 · Cited by 927
“While machines are able to learn complex prediction rules by minimizing their training error, data are often marred by selection biases, confounding factors, and other peculiarities [49, 48, 23].”
BackgroundDetection and Classification of Acoustic Scenes and Events
Stowell, D., Giannoulis, D., Benetos, E., Lagrange, M., & Plumbley, M. D. (2015) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2015.2428998 · Cited by 600
Ross, A., & Doshi-Velez, F. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11504 · Cited by 589
An Introduction to Neural Information Retrieval
Mitra, B., & Craswell, N. (2018) · Foundations and Trends® in Information Retrieval · doi:10.1561/1500000061 · Cited by 317
Experimenting with musically motivated convolutional neural networks
Pons, J., Lidy, T., & Serra, X. (2016) · 2016 14th International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi.2016.7500246 · Cited by 132
“This is specially relevant for the MIR field since it has already been pointed out that machine learning algorithms are learning how to ”reproduce the ground truth” rather than learning musical concepts [21].”
BackgroundCLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning
Johnson, J., Hariharan, B., van der Maaten, L., Fei-Fei, L., Zitnick, C. L., & Girshick, R. (2016) · arXiv · doi:10.48550/arxiv.1612.06890 · Cited by 40
Dataset artefacts in anti-spoofing systems: A case study on the ASVspoof 2017 benchmark
Chettri, B., Benetos, E., & Sturm, B. L. T. (2020) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2020.3036777 · Cited by 35
“The trustworthiness of models trained on data containing artefacts is therefore called into question; some can behave much like a “horse” [32], [44], i.”
BackgroundSelf-citation
Metadata
- Authors
- Sturm, B. L.
- Venue
- IEEE Transactions on Multimedia
- Published
- 2014-10
- Volume
- 16
- Issue
- 6
- Pages
- 1636-1644
- ISSN
- 1520-9210 (ISSN-L)
- 1941-0077
- OpenAlex
- W2074619556
- Cited by
- 173
- References
- 0
- FWCI
- 15.51
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.