# Speech-Music Separation on WSJ0 music Source: [Speech-Music Separation on WSJ0 music]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:02:56.058Z Evaluation of speech and music separation performance on the WSJ0 music dataset, measured using metrics like SI-SNRi and SDRi. 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 | Speech-Music Separation | | Dataset (including any stated split) | WSJ0 music | | Metric | SI-SNRi | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 2 of 2 | | 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 - [SI-SNRi](): Higher is better; unit: SCALAR. - [SDRi](): Higher is better; unit: SCALAR. ## Recorded results | Method | SI-SNRi | Result date | Report paper | | --- | --- | --- | --- | | GALR | 15.9 | Not recorded | 68fa690f1e209131cea1fdba | | DPRNN | 14.5 | Not recorded | 68fa690f1e209131cea1fdba | ### GALR SI-SNRi: 15.9. Result ID: 698d958f8b517eb433228134. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"2.3M"}. This record does not assert independent reproduction. ### DPRNN SI-SNRi: 14.5. Result ID: 698d958f8b517eb433228133. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"2.6M"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.