Voice Transformation algorithms

eagle-i ID

Resource Type

Properties

1. Resource Description

   These algorithms are for state-of-the-art voice transformation to create new synthetic voices. VTmax uses an LSF vocoder speech model to train the transformation and generate new speech files. VTmin is useful for cases in which only low-quality existing voice recordings are available.

2. Additional Name

   VT algorithms

3. Used by

   Center for Spoken Language Understanding

4. Related Publication or Documentation

   Evaluation of speaker mimic technology for personalizing SGD voices

5. Developed by

   Klabbers-Judd, Esther, Ph.D.

6. Developed by

   Kain, Alexander, Ph.D.

7. Developed by

   van Santen, Jan P.H., Ph.D.