A supervised mixture of experts, routed by fixed bandwidth and task labels, improves multi-task ASR/ST over hard parameter sharing while keeping active parameters constant.
Sources of degradation of speech recognition in the telephone network,
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.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts
A supervised mixture of experts, routed by fixed bandwidth and task labels, improves multi-task ASR/ST over hard parameter sharing while keeping active parameters constant.