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.
Since the number of layers has a linear relationship with computational cost, reduc- ing them benefits resource-constrained on-device applications
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.AS 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 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.