This paper presents an end-to-end high-quality singing voice synthesis (...
For text-to-speech (TTS) synthesis, prosodic structure prediction (PSP) ...
Abstract: Cover song identification (CSI) focuses on finding the same mu...
Non-parallel data voice conversion (VC) have achieved considerable
break...
Previously proposed FullSubNet has achieved outstanding performance in D...
Generating 3D speech-driven talking head has received more and more atte...
In this paper, we present a generic and robust multimodal synthesis syst...