Login / Signup

Improving Generalizability of Distilled Self-Supervised Speech Processing Models Under Distorted Settings.

Kuan-Po HuangYu-Kuan FuTsu-Yuan HsuFabian Ritter GutierrezFan-Lin WangLiang-Hsuan TsengYu ZhangHung-yi Lee
Published in: SLT (2022)
Keyphrases
  • speech processing
  • signal processing
  • information retrieval
  • speech recognition
  • artificial intelligence
  • generative model
  • multimedia systems