Search Results for author:
Found 2 papers, 0 papers with code
UniTTS: Residual Learning of Unified Embedding Space for Speech Style Control
We propose a novel high-fidelity expressive speech synthesis model, UniTTS, that learns and controls overlapping style attributes avoiding interference.
Fast DCTTS: Efficient Deep Convolutional Text-to-Speech
We propose an end-to-end speech synthesizer, Fast DCTTS, that synthesizes speech in real time on a single CPU thread.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
