List your company

Target Speech Extraction on Relative Cue-based TSE Mixtures (test)

18SI-SDRiTF-Locoformer TSE
-2.6962.6778.0513.423Mar 1, 2026

Evaluation results

MethodLinks
TF-Locoformer TSEFramework Stage=Two-Stage, Cue Type=Temporal Order2026.03183.4599.8
TF-Locoformer TSEFramework Stage=Two-Stage, Cue Type=All Cue2026.0317.43.4199.8
TF-Locoformer TSEFramework Stage=Two-Stage, Cue Type=Language2026.0317.33.4199.3
TF-Locoformer TSEFramework Stage=Two-Stage, Cue Type=Random Cue2026.0317.13.3999.2
TF-Locoformer TSEFramework Stage=Two-Stage, Cue Type=Distance2026.03173.3898.4
TF-Locoformer TSEFramework Stage=Two-Stage, Cue Type=Gender2026.0316.73.3798.1
TF-Locoformer TSEFramework Stage=Two-Stage, Cue Type=Loudness2026.03163.3597.2
TF-Locoformer TSEFramework Stage=Two-Stage, Cue Type=Speaking Duration2026.0315.63.3495.9
TF-Locoformer TSEFramework Stage=Two-Stage, Cue Type=Enrollment Audio2026.0315.23.3195.7
TF-Locoformer TSEFramework Stage=Single-Stage, Cue Type=Temporal Order2026.0315.12.99—
TF-Locoformer TSEFramework Stage=Two-Stage, Cue Type=Pitch Level2026.0314.83.394.6
TF-Locoformer TSEFramework Stage=Single-Stage, Cue Type=Distance2026.0314.62.89—
TF-Locoformer TSEFramework Stage=Single-Stage, Cue Type=All Cue2026.0314.32.88—
TF-Locoformer TSEFramework Stage=Single-Stage, Cue Type=Loudness2026.0313.72.84—
TF-Locoformer TSEFramework Stage=Single-Stage, Cue Type=Random Cue2026.0313.22.7—
TF-Locoformer TSEFramework Stage=Two-Stage, Cue Type=Speaking Rate2026.0313.13.2791.3
TF-Locoformer TSEFramework Stage=Single-Stage, Cue Type=Speaking Duration2026.03132.8—
TF-Locoformer TSEFramework Stage=Single-Stage, Cue Type=Gender2026.0312.82.75—
TF-Locoformer TSEFramework Stage=Single-Stage, Cue Type=Pitch Level2026.0312.82.75—
TF-Locoformer TSEFramework Stage=Two-Stage, Cue Type=Transcription2026.0312.53.2290.4
TF-Locoformer TSEFramework Stage=Single-Stage, Cue Type=Language2026.0311.42.67—
TF-Locoformer TSEFramework Stage=Two-Stage, Cue Type=Pitch Range2026.0311.33.1488.7
TF-Locoformer TSEFramework Stage=Two-Stage, Cue Type=Emotion2026.0310.33.187.2
TF-Locoformer TSEFramework Stage=Single-Stage, Cue Type=Pitch Range2026.0392.47—
DPT-based TSEFramework Stage=Single-Stage, Cue Type=All Cue2026.038.91.8—
DPT-based TSEFramework Stage=Single-Stage, Cue Type=Gender2026.038.81.8—
TF-Locoformer TSEFramework Stage=Single-Stage, Cue Type=Transcription2026.038.72.47—
DPT-based TSEFramework Stage=Single-Stage, Cue Type=Loudness2026.038.71.8—
DPT-based TSEFramework Stage=Single-Stage, Cue Type=Temporal Order2026.038.71.85—
DPT-based TSEFramework Stage=Single-Stage, Cue Type=Random Cue2026.038.41.78—
DPT-based TSEFramework Stage=Single-Stage, Cue Type=Distance2026.038.31.78—
DPT-based TSEFramework Stage=Single-Stage, Cue Type=Pitch Level2026.037.91.77—
TF-Locoformer TSEFramework Stage=Single-Stage, Cue Type=Speaking Rate2026.037.92.44—
TF-Locoformer TSEFramework Stage=Single-Stage, Cue Type=Emotion2026.037.82.44—
DPT-based TSEFramework Stage=Single-Stage, Cue Type=Speaking Duration2026.037.41.79—
DPT-based TSEFramework Stage=Single-Stage, Cue Type=Language2026.035.51.71—
DPT-based TSEFramework Stage=Single-Stage, Cue Type=Pitch Range2026.035.31.68—
DPT-based TSEFramework Stage=Single-Stage, Cue Type=Emotion2026.034.91.56—
DPT-based TSEFramework Stage=Single-Stage, Cue Type=Transcription2026.034.31.67—
DPT-based TSEFramework Stage=Single-Stage, Cue Type=Speaking Rate2026.0341.68—
DPT-based TSEFramework Stage=Single-Stage, Cue Type=Age Category2026.03-11.38—
TF-Locoformer TSEFramework Stage=Two-Stage, Cue Type=Age Category2026.03-1.62.4564.3
TF-Locoformer TSEFramework Stage=Single-Stage, Cue Type=Age Category2026.03-1.91.71—