Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Subjective Speech Evaluation on Sarcastic Speech Synthesis Dataset
Loading...
3.8
NMOS
Ground Truth
1.928
2.414
2.9
3.386
Oct 8, 2025
NMOS
SMOS
Updated 1mo ago
Evaluation Results
Method
Method
Links
NMOS
SMOS
Ground Truth
Semantic Cue Type=-, P...
2025.10
3.8
4.5
w/ LoRA + RAG
Semantic Cue Type=✓, P...
2025.10
2.7
3.8
Baseline
Semantic Cue Type=-, P...
2025.10
2.6
3.2
w/ LLaMA 3-LoRA
Semantic Cue Type=✓, P...
2025.10
2.6
3.8
w/ RAG
Semantic Cue Type=-, P...
2025.10
2.6
3.7
w/ BERT
Semantic Cue Type=✓, P...
2025.10
2.5
3.1
w/ LLaMA 3
Semantic Cue Type=✓, P...
2025.10
2
2.6
Feedback
Search any
task
Search any
task