no code implementations • 7 May 2024 • Amit Eliav, Aaron Taub, Renana Opochinsky, Sharon Gannot
In this paper, we propose a model which can generate a singing voice from normal speech utterance by harnessing zero-shot, many-to-many style transfer learning.
no code implementations • 11 Mar 2024 • Amit Eliav, Sharon Gannot
We present a deep-learning approach for the task of Concurrent Speaker Detection (CSD) using a modified transformer model.