Decoding Strategies for Diffusion-Based ASR: A Systematic Evaluation of Confidence-Based Thresholding

Ähnliche Einträge

• Efficient Training for Multilingual Visual Speech Recognition: Pre-training with Discretized Visual Speech Representation
  von: Kim, Minsu, et al.
  Veröffentlicht: (2024)
• MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens
  von: Yeo, Jeong Hun, et al.
  Veröffentlicht: (2025)
• Lip Reading for Low-resource Languages by Learning and Combining General Speech Knowledge and Language-specific Knowledge
  von: Kim, Minsu, et al.
  Veröffentlicht: (2023)
• Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations
  von: Yeo, Jeong Hun, et al.
  Veröffentlicht: (2025)
• Towards Inclusive Communication: A Unified Framework for Generating Spoken Language from Sign, Lip, and Audio
  von: Yeo, Jeong Hun, et al.
  Veröffentlicht: (2025)