MSRS: Training Multimodal Speech Recognition Models from Scratch with Sparse Mask Optimization

Documenti analoghi

• Large Language Models are Strong Audio-Visual Speech Recognition Learners
  di: Cappellazzo, Umberto, et al.
  Pubblicazione: (2024)
• RT-LA-VocE: Real-Time Low-SNR Audio-Visual Speech Enhancement
  di: Chen, Honglie, et al.
  Pubblicazione: (2024)
• Full-Rank No More: Low-Rank Weight Training for Modern Speech Recognition Models
  di: Fernandez-Lopez, Adriana, et al.
  Pubblicazione: (2024)
• Revival with Voice: Multi-modal Controllable Text-to-Speech Synthesis
  di: Kim, Minsu, et al.
  Pubblicazione: (2025)
• Omni-AVSR: Towards Unified Multimodal Speech Recognition with Large Language Models
  di: Cappellazzo, Umberto, et al.
  Pubblicazione: (2025)