Login / Signup

Using phone and diphone based acoustic models for voice conversion: a step towards creating voice fonts.

Arun KumarAshish Verma
Published in: ICASSP (1) (2003)
Keyphrases
  • acoustic models
  • speech recognition
  • emotion recognition
  • neural network
  • feature vectors
  • multimedia
  • natural language
  • natural language processing
  • video streams