# Track-to-track modeling on Codec Benchmark Vocal to Accompaniment

Source: [Track-to-track modeling on Codec Benchmark Vocal to Accompaniment](<https://www.sota2.com/research/sota/track-to-track-modeling-on-codec-benchmark-vocal-to-accompaniment>)

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

Data updated: 2026-04-02T09:33:23.570Z

Evaluation of track-to-track modeling performance on the Codec Benchmark Vocal to Accompaniment dataset, assessed using accuracy metrics (@1, @10, @50) and BPT scores (cnBPT, enBPT).

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 | Track-to-track modeling |
| Dataset (including any stated split) | Codec Benchmark Vocal to Accompaniment |
| Metric | Accuracy @1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Accuracy @1](<https://www.sota2.com/research/sota/track-to-track-modeling-on-codec-benchmark-vocal-to-accompaniment.md?metric=Accuracy%20%401>): Higher is better; unit: PERCENT.

- [Accuracy @10](<https://www.sota2.com/research/sota/track-to-track-modeling-on-codec-benchmark-vocal-to-accompaniment.md?metric=Accuracy%20%4010>): Higher is better; unit: PERCENT.

- [Accuracy @50](<https://www.sota2.com/research/sota/track-to-track-modeling-on-codec-benchmark-vocal-to-accompaniment.md?metric=Accuracy%20%4050>): Higher is better; unit: PERCENT.

- [CN BPT Score](<https://www.sota2.com/research/sota/track-to-track-modeling-on-codec-benchmark-vocal-to-accompaniment.md?metric=CN%20BPT%20Score>): Higher is better; unit: SCALAR.

- [EN BPT Score](<https://www.sota2.com/research/sota/track-to-track-modeling-on-codec-benchmark-vocal-to-accompaniment.md?metric=EN%20BPT%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy @1 | Result date | Report paper |
| --- | --- | --- | --- |
| MuCodec (LeVo) | 17 | Not recorded | 692689a2d6b0dd33429304ad |
| X-Codec (YuE) | 15 | Not recorded | 692689a2d6b0dd33429304ad |
| DuoTok | 13 | Not recorded | 692689a2d6b0dd33429304ad |

### MuCodec (LeVo)

Accuracy @1: 17. Result ID: 69ce371347f34ce924b7b22f.

[Reporting paper](<https://www.sota2.com/research/paper/692689a2d6b0dd33429304ad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79731e209131cea7db13.md>)

Recorded evaluation configuration: {"Size":"2×16384"}. This record does not assert independent reproduction.

### X-Codec (YuE)

Accuracy @1: 15. Result ID: 69ce371347f34ce924b7b22e.

[Reporting paper](<https://www.sota2.com/research/paper/692689a2d6b0dd33429304ad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b451e209131cea876fc.md>)

Recorded evaluation configuration: {"Size":"8×1024"}. This record does not assert independent reproduction.

### DuoTok

Accuracy @1: 13. Result ID: 69ce371347f34ce924b7b230.

[Reporting paper](<https://www.sota2.com/research/paper/692689a2d6b0dd33429304ad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692689a2d6b0dd33429304ad.md>)

Recorded evaluation configuration: {"Size":"2×32768"}. This record does not assert independent reproduction.

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