In a five-language zero-shot TTS study, no single duration prediction strategy dominates: speaker-prompted durations help some languages, infilling durations help others, and results vary by metric.
Title resolution pending
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
-
Technical report: Impact of Duration Prediction on Speaker-specific TTS for Indian Languages
In a five-language zero-shot TTS study, no single duration prediction strategy dominates: speaker-prompted durations help some languages, infilling durations help others, and results vary by metric.