CLD integrates convex optimization and ADMM in JAX to deliver 97-98% accuracy for language detection robust to accents under low-resource conditions, with claimed theoretical stability guarantees.
ADMM makes this problem tractable by allowing the optimization to be performed in a batched, multi-GPU parallel fashion (especially when implemented in JAX)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Convex Low-resource Accent-Robust Language Detection in Speech Recognition
CLD integrates convex optimization and ADMM in JAX to deliver 97-98% accuracy for language detection robust to accents under low-resource conditions, with claimed theoretical stability guarantees.