TICL: Text-Embedding KNN For Speech In-Context Learning Unlocks Speech Recognition Abilities of Large Multimodal Models

Documenti analoghi

• TICL+: A Case Study On Speech In-Context Learning for Children's Speech Recognition
  di: Zheng, Haolong, et al.
  Pubblicazione: (2025)
• SALSA: Speech Aware LLM Adaptation via Learned Steering Activation Vectors
  di: Yegorova, Yekaterina, et al.
  Pubblicazione: (2026)
• MLLM-based Speech Recognition: When and How is Multimodality Beneficial?
  di: Guan, Yiwen, et al.
  Pubblicazione: (2025)
• Target Speech Diarization with Multimodal Prompts
  di: Jiang, Yidi, et al.
  Pubblicazione: (2024)
• MF-AED-AEC: Speech Emotion Recognition by Leveraging Multimodal Fusion, Asr Error Detection, and Asr Error Correction
  di: He, Jiajun, et al.
  Pubblicazione: (2024)