Joint-marginal alignment plus adaptive weighting in speech VAE distillation yields the best combined performance on reconstruction, understanding, and generation tasks.
Low frame-rate speech codec: a codec designed for fast high-quality speech LLM train- ing and inference,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
On the Distillation Loss Functions of Speech VAE for Unified Reconstruction, Understanding, and Generation
Joint-marginal alignment plus adaptive weighting in speech VAE distillation yields the best combined performance on reconstruction, understanding, and generation tasks.