VoTSpeech: Decoupling Voice Design from Speech Generation in Instruction-Following TTS
VoTSpeech is proposed, which decouples voice design from speech generation via an explicit intermediate voice latent, built on a shared language model backbone and performs strongly on InstructTTSEval-ZH, demonstrating competitive capabilities against strong open-source models while maintaining high naturalness.
Wen-Bing Yang, Qi-Hang Lu, Zi-Han Sun et al.
· 0 citations