# Chord Segmentation on BTC (test)

Source: [Chord Segmentation on BTC (test)](<https://www.sota2.com/research/sota/chord-segmentation-on-btc-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-28T10:21:24.444Z

Evaluation of chord segmentation performance on the test split of the BTC dataset, reporting underestimation, overestimation, and mean error rates.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Chord Segmentation |
| Dataset (including any stated split) | BTC (test) |
| Metric | Underestimation Rate |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 5 of 5 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Underestimation Rate](<https://www.sota2.com/research/sota/chord-segmentation-on-btc-test.md?metric=Underestimation%20Rate>): Lower is better; unit: PERCENT.

- [Overestimation Rate](<https://www.sota2.com/research/sota/chord-segmentation-on-btc-test.md?metric=Overestimation%20Rate>): Lower is better; unit: PERCENT.

- [Mean Error Rate](<https://www.sota2.com/research/sota/chord-segmentation-on-btc-test.md?metric=Mean%20Error%20Rate>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Underestimation Rate | Result date | Report paper |
| --- | --- | --- | --- |
| TE-DM | 88.6 | Not recorded | 69f03f7955a3c32af89fa533 |
| TE-DS | 89.3 | Not recorded | 69f03f7955a3c32af89fa533 |
| TE | 89.5 | Not recorded | 69f03f7955a3c32af89fa533 |
| pTE-DS | 89.8 | Not recorded | 69f03f7955a3c32af89fa533 |
| BTC | 90.1 | Not recorded | 69f03f7955a3c32af89fa533 |

### TE-DM

Underestimation Rate: 88.6. Result ID: 69f0895747f34ce924d71d22.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7955a3c32af89fa533.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f03f7955a3c32af89fa533.md>)

Recorded evaluation configuration: {"Token representation":"Discrete Melodies"}. This record does not assert independent reproduction.

### TE-DS

Underestimation Rate: 89.3. Result ID: 69f0895747f34ce924d71d23.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7955a3c32af89fa533.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f03f7955a3c32af89fa533.md>)

Recorded evaluation configuration: {"Token representation":"Discrete Segments"}. This record does not assert independent reproduction.

### TE

Underestimation Rate: 89.5. Result ID: 69f0895747f34ce924d71d21.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7955a3c32af89fa533.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### pTE-DS

Underestimation Rate: 89.8. Result ID: 69f0895747f34ce924d71d24.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7955a3c32af89fa533.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f03f7955a3c32af89fa533.md>)

Recorded evaluation configuration: {"Token representation":"Discrete Segments","Pre-training":"true"}. This record does not assert independent reproduction.

### BTC

Underestimation Rate: 90.1. Result ID: 69f0895747f34ce924d71d25.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7955a3c32af89fa533.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65fe1e209131cea0dcce.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.