A Simple Method to Enhance Pre-trained Language Models with Speech Tokens for Classification

Documenti analoghi

• SpeechCraft: A Fine-grained Expressive Speech Dataset with Natural Language Description
  di: Jin, Zeyu, et al.
  Pubblicazione: (2024)
• Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs
  di: Song, Dingjie, et al.
  Pubblicazione: (2024)
• SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music Processing
  di: Ma, Ziyang, et al.
  Pubblicazione: (2026)
• A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding
  di: Lu, Jinghui, et al.
  Pubblicazione: (2024)
• UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal Prompts
  di: Cheng, Zhi-Qi, et al.
  Pubblicazione: (2024)