REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR

Documenti analoghi

• CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems
  di: Wu, Haibin, et al.
  Pubblicazione: (2024)
• Leave No Knowledge Behind During Knowledge Distillation: Towards Practical and Effective Knowledge Distillation for Code-Switching ASR Using Realistic Data
  di: Tseng, Liang-Hsuan, et al.
  Pubblicazione: (2024)
• TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling
  di: Tseng, Liang-Hsuan, et al.
  Pubblicazione: (2025)
• Mitigating Subgroup Disparities in Multi-Label Speech Emotion Recognition: A Pseudo-Labeling and Unsupervised Learning Approach
  di: Lin, Yi-Cheng, et al.
  Pubblicazione: (2025)
• MI-Fuse: Label Fusion for Unsupervised Domain Adaptation with Closed-Source Large-Audio Language Model
  di: Huang, Hsiao-Ying, et al.
  Pubblicazione: (2025)