From Words to Waves: Analyzing Concept Formation in Speech and Text-Based Foundation Models

Documenti analoghi

• Once Correct, Still Wrong: Counterfactual Hallucination in Multilingual Vision-Language Models
  di: Mousi, Basel, et al.
  Pubblicazione: (2026)
• Speech Representation Analysis based on Inter- and Intra-Model Similarities
  di: Kheir, Yassine El, et al.
  Pubblicazione: (2024)
• Children's Speech Recognition through Discrete Token Enhancement
  di: Sukhadia, Vrunda N., et al.
  Pubblicazione: (2024)
• Multi-Task Instruction Tuning via Data Scheduling for Low-Resource Arabic AudioLLMs
  di: Bhatti, Hunzalah Hassan, et al.
  Pubblicazione: (2026)
• Word-Level Emotional Expression Control in Zero-Shot Text-to-Speech Synthesis
  di: Wang, Tianrui, et al.
  Pubblicazione: (2025)