Should you use a probabilistic duration model in TTS? Probably! Especially for spontaneous speech

Documenti analoghi

• Matcha-TTS: A fast TTS architecture with conditional flow matching
  di: Mehta, Shivam, et al.
  Pubblicazione: (2023)
• Unified speech and gesture synthesis using flow matching
  di: Mehta, Shivam, et al.
  Pubblicazione: (2023)
• Fake it to make it: Using synthetic data to remedy the data shortage in joint multimodal speech-and-gesture synthesis
  di: Mehta, Shivam, et al.
  Pubblicazione: (2024)
• Look and Tell: A Dataset for Multimodal Grounding Across Egocentric and Exocentric Views
  di: Deichler, Anna, et al.
  Pubblicazione: (2025)
• IMUVIE: Pickup Timeline Action Localization via Motion Movies
  di: Clapham, John, et al.
  Pubblicazione: (2024)