Noise-Robust AV-ASR Using Visual Features Both in the Whisper Encoder and Decoder

Documenti analoghi

• Extending Whisper with prompt tuning to target-speaker ASR
  di: Ma, Hao, et al.
  Pubblicazione: (2023)
• mWhisper-Flamingo for Multilingual Audio-Visual Noise-Robust Speech Recognition
  di: Rouditchenko, Andrew, et al.
  Pubblicazione: (2025)
• Revisiting Acoustic Features for Robust ASR
  di: Shah, Muhammad A., et al.
  Pubblicazione: (2024)
• Diagnostic-Driven Layer-Wise Compensation for Post-Training Quantization of Encoder-Decoder ASR Models
  di: Wang, Xinyu, et al.
  Pubblicazione: (2026)
• Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation
  di: Rouditchenko, Andrew, et al.
  Pubblicazione: (2024)