UniTTS: Residual Learning of Unified Embedding Space for Speech Style Control. (arXiv:2106.11171v2 [eess.AS] UPDATED)

We propose a novel high-fidelity expressive speech synthesis model, UniTTS,
that learns and controls overlapping style attributes avoiding interference.
UniTTS represents multiple style attributes in a single unified embedding space
by the residuals between the phoneme embeddings before and after applying the
attributes. The proposed method is especially effective in controlling multiple
attributes that are difficult to separate cleanly, such as speaker ID and
emotion, because it minimizes redundancy when adding variance in speaker ID and
emotion, and additionally, predicts …

arxiv embedding learning space speech