Layer-wise Minimal Pair Probing Reveals Contextual Grammatical-Conceptual Hierarchy in Speech Representations

Documenti analoghi

• SightSound-R1: Cross-Modal Reasoning Distillation from Vision to Audio Language Models
  di: Wang, Qiaolin, et al.
  Pubblicazione: (2025)
• Listen, Chat, and Remix: Text-Guided Soundscape Remixing for Enhanced Auditory Experience
  di: Jiang, Xilin, et al.
  Pubblicazione: (2024)
• Style-Talker: Finetuning Audio Language Model and Style-Based Text-to-Speech Model for Fast Spoken Dialogue Generation
  di: Li, Yinghao Aaron, et al.
  Pubblicazione: (2024)
• Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separation
  di: Jiang, Xilin, et al.
  Pubblicazione: (2024)
• Just ASR + LLM? A Study on Speech Large Language Models' Ability to Identify and Understand Speaker in Spoken Dialogue
  di: Wu, Junkai, et al.
  Pubblicazione: (2024)