Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates

Ähnliche Einträge

• Effective and Efficient Mixed Precision Quantization of Speech Foundation Models
  von: Xu, Haoning, et al.
  Veröffentlicht: (2025)
• Towards LLM-Empowered Fine-Grained Speech Descriptors for Explainable Emotion Recognition
  von: Chen, Youjun, et al.
  Veröffentlicht: (2025)
• Phone-purity Guided Discrete Tokens for Dysarthric Speech Recognition
  von: Wang, Huimeng, et al.
  Veröffentlicht: (2025)
• One-pass Multiple Conformer and Foundation Speech Systems Compression and Quantization Using An All-in-one Neural Model
  von: Li, Zhaoqing, et al.
  Veröffentlicht: (2024)
• On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition
  von: HU, Shujie, et al.
  Veröffentlicht: (2025)