A streaming, layer-reduced WavLM predicts discrete speech units with 50% fewer FLOPs, but the paper's reported low error rates for that configuration are contradicted by its own tables.
Knowledge distillation (KD) is of- ten used to reduce the size of S3Ms, such as DistilHuBERT
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
REJECT 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
On-device Streaming Discrete Speech Units
A streaming, layer-reduced WavLM predicts discrete speech units with 50% fewer FLOPs, but the paper's reported low error rates for that configuration are contradicted by its own tables.