Investigating Zero-Shot Generalizability on Mandarin-English Code-Switched ASR and Speech-to-text Translation of Recent Foundation Models with Self-Supervision and Weak Supervision

Documenti analoghi

• Zero Resource Code-switched Speech Benchmark Using Speech Utterance Pairs For Multiple Spoken Languages
  di: Huang, Kuan-Po, et al.
  Pubblicazione: (2023)
• Gender Bias in Instruction-Guided Speech Synthesis Models
  di: Kuan, Chun-Yi, et al.
  Pubblicazione: (2025)
• Speech-IFEval: Evaluating Instruction-Following and Quantifying Catastrophic Forgetting in Speech-Aware Language Models
  di: Lu, Ke-Han, et al.
  Pubblicazione: (2025)
• Enhancing Multilingual ASR for Unseen Languages via Language Embedding Modeling
  di: Huang, Shao-Syuan, et al.
  Pubblicazione: (2024)
• Do Prompts Really Prompt? Exploring the Prompt Understanding Capability of Whisper
  di: Yang, Chih-Kai, et al.
  Pubblicazione: (2024)