no code implementations • 3 Dec 2020 • Josef Schlittenlacher, Thomas Baer
Transfer learning led to a quick adaptation of the produced spectra from original speech to individually amplified speech, resulted in high speech quality and intelligibility, and thus gives us a way to train an individual TTS system efficiently.
no code implementations • 24 May 2019 • Josef Schlittenlacher, Richard E. Turner, Brian C. J. Moore
The DNN was trained using the output of a more complex model, called the Cambridge loudness model.