Denoising GER: A Noise-Robust Generative Error Correction with LLM for Speech Recognition

Documenti analoghi

• Wav2DF-TSL: Two-stage Learning with Efficient Pre-training and Hierarchical Experts Fusion for Robust Audio Deepfake Detection
  di: Hao, Yunqi, et al.
  Pubblicazione: (2025)
• Enhancing Self-Supervised Speaker Verification Using Similarity-Connected Graphs and GCN
  di: Sun, Zhaorui, et al.
  Pubblicazione: (2025)
• Are Deep Speech Denoising Models Robust to Adversarial Noise?
  di: Schwarzer, Will, et al.
  Pubblicazione: (2025)
• MMGER: Multi-modal and Multi-granularity Generative Error Correction with LLM for Joint Accent and Speech Recognition
  di: Mu, Bingshen, et al.
  Pubblicazione: (2024)
• Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition
  di: Mu, Bingshen, et al.
  Pubblicazione: (2025)