Login / Signup

Diff-SV: A Unified Hierarchical Framework for Noise-Robust Speaker Verification Using Score-Based Diffusion Probabilistic Models.

Ju-ho KimJungwoo HeoHyun-seo ShinChan-yeong LimHa-Jin Yu
Published in: CoRR (2023)
Keyphrases
  • probabilistic model
  • speaker verification
  • noisy environments
  • low level
  • noise reduction
  • neural network
  • information retrieval
  • pattern recognition
  • mixture model