notesum.ai
Published at December 9Source Separation & Automatic Transcription for Music
cs.SD
cs.AI
eess.AS
Released Date: December 9, 2024
Authors: Bradford Derby1, Lucas Dunker, Samarth Galchar, Shashank Jarmale, Akash Setti
Aff.: 1Northeastern University

| Metric | Description |
|---|---|
| SNRI | Improvement in SNR over using the mixture as the estimate. |
| SD-SDRi | Improvement in SD-SDR over using the mixture as the estimate. |
| SI-SDRi | Improvement in SI-SDR over using the mixture as the estimate. |
| SRR | The source-to-rescaled-source ratio. |
| SNR | Signal-to-noise ratio. |
| SD-SDR | Scale-dependent source-to-distortion ratio. |
| SI-SAR | Scale-invariant source-to-artifact ratio. |
| SI-SIR | Scale-invariant source-to-interference ratio. |
| SI-SDR | Scale-invariant source-to-distortion ratio. |