Novel Parasitic Dual-Scale Modeling for Efficient and Accurate Multilingual Speech Translation

Documenti analoghi

• MFLA: Monotonic Finite Look-ahead Attention for Streaming Speech Recognition
  di: Xia, Yinfeng, et al.
  Pubblicazione: (2025)
• SpeechFake: A Large-Scale Multilingual Speech Deepfake Dataset Incorporating Cutting-Edge Generation Methods
  di: Huang, Wen, et al.
  Pubblicazione: (2025)
• Scale This, Not That: Investigating Key Dataset Attributes for Efficient Speech Enhancement Scaling
  di: Zhang, Leying, et al.
  Pubblicazione: (2024)
• SimulMEGA: MoE Routers are Advanced Policy Makers for Simultaneous Speech Translation
  di: Le, Chenyang, et al.
  Pubblicazione: (2025)
• DQ-Whisper: Joint Distillation and Quantization for Efficient Multilingual Speech Recognition
  di: Shao, Hang, et al.
  Pubblicazione: (2023)