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.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
REJECT 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.