LOPA with SALR achieves RMSE 0.361 on spoken language assessment by enforcing ordinal prototype alignment in latent space from a frozen Whisper encoder.
The NTNU System at the S&I Challenge 2025 SLA Open Track,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LOPA: Enhancing Spoken Language Assessment via Latent Ordinal Prototype Alignment
LOPA with SALR achieves RMSE 0.361 on spoken language assessment by enforcing ordinal prototype alignment in latent space from a frozen Whisper encoder.