VoiceStar uses a progress-based rotary position embedding and mixed prompt training to give zero-shot voice cloning precise duration control and much longer output than training clips.
Vall-t: Decoder-only generative transducer for robust and decoding- controllable text-to-speech
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
VoiceStar: Robust Zero-Shot Autoregressive TTS with Duration Control and Extrapolation
VoiceStar uses a progress-based rotary position embedding and mixed prompt training to give zero-shot voice cloning precise duration control and much longer output than training clips.