A dynamic frequency-adaptive knowledge distillation method, using the steepest point in the running maximum of the teacher spectrum as a crossover, improves speech enhancement student models by small PESQ margins over logit-based KD baselines.
A convolutional recurrent neural network for real- time speech enhancement
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Dynamic Frequency-Adaptive Knowledge Distillation for Speech Enhancement
A dynamic frequency-adaptive knowledge distillation method, using the steepest point in the running maximum of the teacher spectrum as a crossover, improves speech enhancement student models by small PESQ margins over logit-based KD baselines.