Login / Signup

FA-ExU-Net: The Simultaneous Training of an Embedding Extractor and Enhancement Model for a Speaker Verification System Robust to Short Noisy Utterances.

Ju-ho KimJungwoo HeoHyun-seo ShinChan-yeong LimHa-Jin Yu
Published in: IEEE ACM Trans. Audio Speech Lang. Process. (2024)
Keyphrases
  • speaker verification
  • probabilistic model
  • neural network
  • pattern recognition
  • low level
  • neural network model
  • noisy environments
  • learning algorithm
  • feature space