Adding multiple codebooks, a KL-divergence regularizer, and cluster-specific codebooks to BEST-RQ improves LibriSpeech ASR word error rates by up to 30.6% relative with faster convergence.
Hubert: Self-supervised speech representation learning by masked prediction of hidden units,
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
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Optimized Self-supervised Training with BEST-RQ for Speech Recognition
Adding multiple codebooks, a KL-divergence regularizer, and cluster-specific codebooks to BEST-RQ improves LibriSpeech ASR word error rates by up to 30.6% relative with faster convergence.