# High-fidelity Waveform Generation on MUSDB18-HQ (test) Source: [High-fidelity Waveform Generation on MUSDB18-HQ (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:21:24.262Z Evaluation of high-fidelity audio waveform generation models using the MUSDB18-HQ test set. Performance is assessed using the Source-domain Mean Opinion Score (SMOS) across various stems (Vocal, Drums, Bass, Others) and the mixture. 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 | High-fidelity waveform generation | | Dataset (including any stated split) | MUSDB18-HQ (test) | | Metric | SMOS (Vocal) | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 0 of 0 | | 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 - [SMOS (Vocal)](): Higher is better; unit: SCALAR. - [SMOS (Drums)](): Higher is better; unit: SCALAR. - [SMOS (Bass)](): Higher is better; unit: SCALAR. - [SMOS (Others)](): Higher is better; unit: SCALAR. - [SMOS (Mixture)](): Higher is better; unit: SCALAR. - [SMOS (Average)](): Higher is better; unit: SCALAR. ## Recorded results | Method | SMOS (Vocal) | Result date | Report paper | | --- | --- | --- | --- | Page 1 of 1. This is an index page, not the full collection.