Who is Speaking or Who is Depressed? A Controlled Study of Speaker Leakage in Speech-Based Depression Detection

Documenti analoghi

• HuLA: Prosody-Aware Anti-Spoofing with Multi-Task Learning for Expressive and Emotional Synthetic Speech
  di: Mahapatra, Aurosweta, et al.
  Pubblicazione: (2025)
• Text-to-Speech for Unseen Speakers via Low-Complexity Discrete Unit-Based Frame Selection
  di: Ulgen, Ismail Rasim, et al.
  Pubblicazione: (2024)
• ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks
  di: Mahapatra, Aurosweta, et al.
  Pubblicazione: (2026)
• Exploring speech style spaces with language models: Emotional TTS without emotion labels
  di: Chandra, Shreeram Suresh, et al.
  Pubblicazione: (2024)
• NaturalVoices: A Large-Scale, Spontaneous and Emotional Podcast Dataset for Voice Conversion
  di: Du, Zongyang, et al.
  Pubblicazione: (2025)