$\text{M}^3\text{PDB}$: A Multimodal, Multi-Label, Multilingual Prompt Database for Speech Generation

Documenti analoghi

• Rare Word Recognition and Translation Without Fine-Tuning via Task Vector in Speech Models
  di: Jing, Ruihao, et al.
  Pubblicazione: (2025)
• High-Fidelity Generative Audio Compression at 0.275kbps
  di: Ma, Hao, et al.
  Pubblicazione: (2026)
• STASE: A spatialized text-to-audio synthesis engine for music generation
  di: Chi, Tutti, et al.
  Pubblicazione: (2025)
• Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty
  di: Xue, Hongfei, et al.
  Pubblicazione: (2025)
• Text adaptation for speaker verification with speaker-text factorized embeddings
  di: Yang, Yexin, et al.
  Pubblicazione: (2025)