A two-stage language-model TTS system uses quantized masked-autoencoder style tokens plus discrete attribute labels to achieve fine-grained style control with stable content.
Textrolspeech: A text style control speech corpus with codec language text-to-speech models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.MM 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
support 1representative citing papers
citing papers explorer
-
Controllable Text-to-Speech Synthesis with Masked-Autoencoded Style-Rich Representation
A two-stage language-model TTS system uses quantized masked-autoencoder style tokens plus discrete attribute labels to achieve fine-grained style control with stable content.