Smaller discrete vocabularies (k = 125 to 1,000), WavLM units, and larger models give the lowest negative log-likelihood in speech language model pre-training.
In: Proceedings of the 34th International Conference on Neural Information Processing Systems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
An Empirical Analysis of Discrete Unit Representations in Speech Language Modeling Pre-training
Smaller discrete vocabularies (k = 125 to 1,000), WavLM units, and larger models give the lowest negative log-likelihood in speech language model pre-training.