Sign in

ICSpk: Interpretable Complex Speaker Embedding Extractor from Raw Waveform.

Junyi PengXiaoyang QuJianzong WangRongzhi GuJing XiaoLukás BurgetJan Cernocký
Published in: Interspeech (2021)
Keyphrases
  • real world
  • high level
  • complex data
  • database
  • similarity measure
  • raw data
  • bayesian networks
  • multiscale
  • high dimensional
  • digital images
  • speech recognition
  • complex systems
  • audio visual