Multi-teacher distillation creates an all-rounder ASR model outperforming both multi-condition and domain-specific baselines by up to 10.4% relative CER.
During the training process, sam- ples in one minibatch are chosen randomly from the mixed data set, and may come from different domains
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Teach an all-rounder with experts in different domains
Multi-teacher distillation creates an all-rounder ASR model outperforming both multi-condition and domain-specific baselines by up to 10.4% relative CER.