• search
    search
  • reviewers
    reviewers
  • feeds
    feeds
  • assignments
    assignments
  • settings
  • logout

Variable Frame Rate-Based Data Augmentation to Handle Speaking-Style Variability for Automatic Speaker Verification.

Amber AfshanJinxi GuoSoo Jin ParkVijay RaviAlan McCreeAbeer Alwan
Published in: INTERSPEECH (2020)
Keyphrases
  • frame rate
  • data sets
  • high quality
  • speaker verification
  • computer vision
  • artificial neural networks
  • image data
  • input data
  • real time
  • video sequences
  • feature space
  • gaussian mixture model