# Instantaneous Pitch Estimation on Bagshaw, Keele, and MIR-1K clean conditions (test)

Source: [Instantaneous Pitch Estimation on Bagshaw, Keele, and MIR-1K clean conditions (test)](<https://www.sota2.com/research/sota/instantaneous-pitch-estimation-on-bagshaw-keele-and-mir-1k-clean-conditions-test>)

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

Data updated: 2026-06-15T07:39:46.334Z

Evaluation of Instantaneous Pitch Estimation performance on the combined test split derived from Bagshaw, Keele, and MIR-1K datasets under clean conditions, measured using Cent Error and specific RPA thresholds.

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 | Instantaneous Pitch Estimation |
| Dataset (including any stated split) | Bagshaw, Keele, and MIR-1K clean conditions (test) |
| Metric | Cent Error (Δc) |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 4 of 4 |
| 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

- [Cent Error (Δc)](<https://www.sota2.com/research/sota/instantaneous-pitch-estimation-on-bagshaw-keele-and-mir-1k-clean-conditions-test.md?metric=Cent%20Error%20(%CE%94c)>): Lower is better; unit: SCALAR.

- [RPA (5 cents)](<https://www.sota2.com/research/sota/instantaneous-pitch-estimation-on-bagshaw-keele-and-mir-1k-clean-conditions-test.md?metric=RPA%20(5%20cents)>): Higher is better; unit: PERCENT.

- [RPA (25 cents)](<https://www.sota2.com/research/sota/instantaneous-pitch-estimation-on-bagshaw-keele-and-mir-1k-clean-conditions-test.md?metric=RPA%20(25%20cents)>): Higher is better; unit: PERCENT.

- [RPA (50 cents)](<https://www.sota2.com/research/sota/instantaneous-pitch-estimation-on-bagshaw-keele-and-mir-1k-clean-conditions-test.md?metric=RPA%20(50%20cents)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Cent Error (Δc) | Result date | Report paper |
| --- | --- | --- | --- |
| Halcyon | 2.45 | Not recorded | 6a2f86eed33dfb23e783bead |
| Wave-U-Net-based fundamental waveform filtering | 28.23 | Not recorded | 6a2f86eed33dfb23e783bead |
| NINJAL | 30.41 | Not recorded | 6a2f86eed33dfb23e783bead |
| IRAPT | 71.69 | Not recorded | 6a2f86eed33dfb23e783bead |

### Halcyon

Cent Error (Δc): 2.45. Result ID: 6a2fac27fbc373592c2bb2a1.

[Reporting paper](<https://www.sota2.com/research/paper/6a2f86eed33dfb23e783bead.md>)

Recorded evaluation configuration: {"Condition":"Clean"}. This record does not assert independent reproduction.

### Wave-U-Net-based fundamental waveform filtering

Cent Error (Δc): 28.23. Result ID: 6a2fac27fbc373592c2bb2a3.

[Reporting paper](<https://www.sota2.com/research/paper/6a2f86eed33dfb23e783bead.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2f86eed33dfb23e783bead.md>)

Recorded evaluation configuration: {"Condition":"Clean"}. This record does not assert independent reproduction.

### NINJAL

Cent Error (Δc): 30.41. Result ID: 6a2fac27fbc373592c2bb2a2.

[Reporting paper](<https://www.sota2.com/research/paper/6a2f86eed33dfb23e783bead.md>)

Recorded evaluation configuration: {"Condition":"Clean"}. This record does not assert independent reproduction.

### IRAPT

Cent Error (Δc): 71.69. Result ID: 6a2fac27fbc373592c2bb2a0.

[Reporting paper](<https://www.sota2.com/research/paper/6a2f86eed33dfb23e783bead.md>)

Recorded evaluation configuration: {"Condition":"Clean"}. This record does not assert independent reproduction.

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