L3-SE reduces linguistic hallucination in LM-based speech enhancement by distilling noise-invariant acoustic-semantic representations from noisy inputs to condition an autoregressive decoder-only language model.
InProceedings of the 23rd international conference on Machine learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
CanonSLR uses frontal-view teacher-student distillation and temporal motion enhancement to boost multi-view continuous sign language recognition, backed by new seven-view benchmarks PT14-MV and CSL-MV created from existing single-view datasets.
citing papers explorer
-
Reducing Linguistic Hallucination in LM-Based Speech Enhancement via Noise-Invariant Acoustic-Semantic Distillation
L3-SE reduces linguistic hallucination in LM-based speech enhancement by distilling noise-invariant acoustic-semantic representations from noisy inputs to condition an autoregressive decoder-only language model.
-
CanonSLR: Canonical-View Guided Multi-View Continuous Sign Language Recognition
CanonSLR uses frontal-view teacher-student distillation and temporal motion enhancement to boost multi-view continuous sign language recognition, backed by new seven-view benchmarks PT14-MV and CSL-MV created from existing single-view datasets.