Combining knowledge distillation with l0 or low-rank pruning improves compressed RNN-T ASR, and joint pruning with fine-tuning gives 8.9% and 13.4% relative WER gains over baseline.
DistilHuBERT: Speech representation learning by layer-wise distillation of hidden-unit BERT,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Synergistic Effects of Knowledge Distillation and Structured Pruning for Self-Supervised Speech Models
Combining knowledge distillation with l0 or low-rank pruning improves compressed RNN-T ASR, and joint pruning with fine-tuning gives 8.9% and 13.4% relative WER gains over baseline.