XEmoRAG: Cross-Lingual Emotion Transfer with Controllable Intensity Using Retrieval-Augmented Generation

Documenti analoghi

• Weakly Supervised Data Refinement and Flexible Sequence Compression for Efficient Thai LLM-based ASR
  di: Shao, Mingchen, et al.
  Pubblicazione: (2025)
• FreeV: Free Lunch For Vocoders Through Pseudo Inversed Mel Filter
  di: Lv, Yuanjun, et al.
  Pubblicazione: (2024)
• FleSpeech: Flexibly Controllable Speech Generation with Various Prompts
  di: Li, Hanzhao, et al.
  Pubblicazione: (2025)
• Boosting Multi-Speaker Expressive Speech Synthesis with Semi-supervised Contrastive Learning
  di: Zhu, Xinfa, et al.
  Pubblicazione: (2023)
• Speaker-agnostic Emotion Vector for Cross-speaker Emotion Intensity Control
  di: Murata, Masato, et al.
  Pubblicazione: (2025)