StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs

Documenti analoghi

• Beyond Transcription: Unified Audio Schema for Perception-Aware AudioLLMs
  di: Zhang, Linhao, et al.
  Pubblicazione: (2026)
• WildSpeech-Bench: Benchmarking End-to-End SpeechLLMs in the Wild
  di: Zhang, Linhao, et al.
  Pubblicazione: (2025)
• Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs
  di: Wang, Dingdong, et al.
  Pubblicazione: (2025)
• Speech-Worthy Alignment for Japanese SpeechLLMs via Direct Preference Optimization
  di: Zhao, Mengjie, et al.
  Pubblicazione: (2026)
• SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models
  di: Zhang, Xin, et al.
  Pubblicazione: (2023)