Login / Signup

The Sound of My Voice: Speaker Representation Loss for Target Voice Separation.

Seongkyu MunSoyeon ChoeJaesung HuhJoon Son Chung
Published in: ICASSP (2020)
Keyphrases
  • synthesized speech
  • voice and data services
  • data sets
  • neural network
  • sound source
  • text to speech
  • database
  • feature space
  • image representation
  • target tracking
  • target detection
  • representation scheme