STSM-FiLM: A FiLM-Conditioned Neural Architecture for Time-Scale Modification of Speech

Documenti analoghi

• HAAQI-Net: A Non-intrusive Neural Music Audio Quality Assessment Model for Hearing Aids
  di: Wisnu, Dyah A. M. G., et al.
  Pubblicazione: (2024)
• Speech Intelligibility Assessment with Uncertainty-Aware Whisper Embeddings and sLSTM
  di: Zezario, Ryandhimas E., et al.
  Pubblicazione: (2025)
• A Study on Zero-Shot Non-Intrusive Speech Intelligibility for Hearing Aids Using Large Language Models
  di: Zezario, Ryandhimas E., et al.
  Pubblicazione: (2025)
• Improving Perceptual Audio Aesthetic Assessment via Triplet Loss and Self-Supervised Embeddings
  di: Wisnu, Dyah A. M. G., et al.
  Pubblicazione: (2025)
• FiPA-SR -- FiLM-Conditioned Perceptually Informed Audio Super-Resolution
  di: Abreu, Wallace, et al.
  Pubblicazione: (2026)