Update README.md

README.md

@@ -11,14 +11,11 @@ datasets:
 - MUSDB18-HQ
 metrics:
 - SDR
-- SIR
-- SAR
 ---
 
-# Sampling-frequency-independent (SFI) Conv-TasNet using frequency-domain SFI convolutional layers trained with MUSDB18-HQ for music source separation
-
-This model was trained by Tomohiko Nakamura using [the codebase](https://github.com/TomohikoNakamura/sfi_convtasnet)).
-It was proposed in [our IEEE/ACM Trans. ASLP paper](https://doi.org/10.1109/TASLP.2022.3203907).
+# Sampling-frequency-independent (SFI) Conv-TasNet trained with the MUSDB18-HQ dataset for music source separation.
+This model was proposed in [our IEEE/ACM Trans. ASLP paper](https://doi.org/10.1109/TASLP.2022.3203907) and works well with untrained sampling frequencies by using sampling-frequency-independent convolutional layers with the frequency domain filter design.
+It was trained by Tomohiko Nakamura using [the codebase](https://github.com/TomohikoNakamura/sfi_convtasnet)).
 This model was trained with 32 kHz-sampled data but works well with untrained sampling frequencies (e.g., 8, 16 kHz).
 
 # License
@@ -42,6 +39,3 @@ Please cite the following paper.
 # Contents
 - Four trained models (seed=40,42,44,47)
 - Evaluation results (json files obtained with the museval library)
-
-# Results on vocal ensemble separation
-