Word-Level ASR Quality Estimation for Efficient Corpus Sampling and Post-Editing through Analyzing Attentions of a Reference-Free Metric

Documenti analoghi

• AutoMode-ASR: Learning to Select ASR Systems for Better Quality and Cost
  di: Gündüz, Ahmet, et al.
  Pubblicazione: (2024)
• Can We Really Repurpose Multi-Speaker ASR Corpus for Speaker Diarization?
  di: Horiguchi, Shota, et al.
  Pubblicazione: (2025)
• EfficientASR: Speech Recognition Network Compression via Attention Redundancy and Chunk-Level FFN Optimization
  di: Wang, Jianzong, et al.
  Pubblicazione: (2024)
• Melodia: Training-Free Music Editing Guided by Attention Probing in Diffusion Models
  di: Yang, Yi, et al.
  Pubblicazione: (2025)
• Enhancing Zero-Shot Multi-Speaker TTS with Negated Speaker Representations
  di: Jeon, Yejin, et al.
  Pubblicazione: (2024)