EME-TTS combines weakly supervised emphasis labels, variance-based pitch and duration features, and an attention block to synthesize emotional speech with controllable, clearly audible word emphasis.
LQN25F020001), and in part by the Key R&D Program of Zhejiang (2025C01104)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
EME-TTS: Unlocking the Emphasis and Emotion Link in Speech Synthesis
EME-TTS combines weakly supervised emphasis labels, variance-based pitch and duration features, and an attention block to synthesize emotional speech with controllable, clearly audible word emphasis.