SimulMEGA: MoE Routers are Advanced Policy Makers for Simultaneous Speech Translation

Documenti analoghi

• Advanced Zero-Shot Text-to-Speech for Background Removal and Preservation with Controllable Masked Speech Prediction
  di: Zhang, Leying, et al.
  Pubblicazione: (2025)
• Novel Parasitic Dual-Scale Modeling for Efficient and Accurate Multilingual Speech Translation
  di: Le, Chenyang, et al.
  Pubblicazione: (2025)
• On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition
  di: HU, Shujie, et al.
  Pubblicazione: (2025)
• Advanced Long-Content Speech Recognition With Factorized Neural Transducer
  di: Gong, Xun, et al.
  Pubblicazione: (2024)
• Flow-TSVAD: Target-Speaker Voice Activity Detection via Latent Flow Matching
  di: Chen, Zhengyang, et al.
  Pubblicazione: (2024)