Sign in

TitaNet: Neural Model for Speaker Representation with 1D Depth-Wise Separable Convolutions and Global Context.

Nithin Rao KoluguriTaejin ParkBoris Ginsburg
Published in: ICASSP (2022)
Keyphrases
  • neural model
  • global context
  • neural network
  • control scheme
  • pairwise
  • recurrent neural networks
  • image representation
  • global information
  • machine learning
  • genetic algorithm
  • image processing