Mamba-based HuBERT models match or exceed Transformer versions on speech tasks while using far less compute for long sequences and streaming ASR.
Multi-resolution Hu- BERT: Multi-resolution Speech Self-Supervised Learning with Masked Unit Prediction,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
An Exploration of Mamba for Speech Self-Supervised Models
Mamba-based HuBERT models match or exceed Transformer versions on speech tasks while using far less compute for long sequences and streaming ASR.