A new TTS system family combines pre-training, supervised fine-tuning, and GRPO reinforcement learning with a 48 kHz codec to produce multilingual speech with in-context voice cloning.
Styletts 2: Towards human-level text-to-speech through style diffusion and adversarial training with large speech language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
TTS-1 Technical Report
A new TTS system family combines pre-training, supervised fine-tuning, and GRPO reinforcement learning with a 48 kHz codec to produce multilingual speech with in-context voice cloning.