Spotlight-TTS improves expressive TTS by quantizing only voiced frames with a rotation trick and by rotating style embeddings to be orthogonal to content while preserving prosody.
With recent advancements in deep learning technology [2, 3, 4], the naturalness of synthesized speech has improved significantly [5, 6]
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.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Spotlight-TTS: Spotlighting the Style via Voiced-Aware Style Extraction and Style Direction Adjustment for Expressive Text-to-Speech
Spotlight-TTS improves expressive TTS by quantizing only voiced frames with a rotation trick and by rotating style embeddings to be orthogonal to content while preserving prosody.