Distillation-based Layer Dropping (DLD): Effective End-to-end Framework for Dynamic Speech Networks

Documenti analoghi

• Input Conditioned Layer Dropping in Speech Foundation Models
  di: Hannan, Abdul, et al.
  Pubblicazione: (2025)
• An Effective Training Framework for Light-Weight Automatic Speech Recognition Models
  di: Hannan, Abdul, et al.
  Pubblicazione: (2025)
• MLMA: Towards Multilingual ASR With Mamba-based Architectures
  di: Ali, Mohamed Nabih, et al.
  Pubblicazione: (2025)
• Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices
  di: Lasbordes, Maxence, et al.
  Pubblicazione: (2025)
• Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach
  di: Cappellazzo, Umberto, et al.
  Pubblicazione: (2025)