Search Results for author:
Found 2 papers, 0 papers with code
Training speech emotion classifier without categorical annotations
There are two paradigms of emotion representation, categorical labeling and dimensional description in continuous space.
TTS voice corpus reduction for audio-book generation
Nowadays, with emerging new voice corpora, voice corpus reduction in expressive TTS becomes more important.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
