SpeechCaps: Advancing Instruction-Based Universal Speech Models with Multi-Talker Speaking Style Captioning

Documenti analoghi

• Speech-IFEval: Evaluating Instruction-Following and Quantifying Catastrophic Forgetting in Speech-Aware Language Models
  di: Lu, Ke-Han, et al.
  Pubblicazione: (2025)
• Fusion of Discrete Representations and Self-Augmented Representations for Multilingual Automatic Speech Recognition
  di: Wang, Shih-heng, et al.
  Pubblicazione: (2024)
• Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech
  di: Huang, Chien-yu, et al.
  Pubblicazione: (2023)
• Advancing Large Language Models to Capture Varied Speaking Styles and Respond Properly in Spoken Conversations
  di: Lin, Guan-Ting, et al.
  Pubblicazione: (2024)
• CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speech
  di: Wang, Helin, et al.
  Pubblicazione: (2025)