MGSC: A Multi-granularity Consistency Framework for Robust End-to-end Asr

Documenti analoghi

• Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data?
  di: Fang, Qingkai, et al.
  Pubblicazione: (2024)
• CTC-based Non-autoregressive Textless Speech-to-Speech Translation
  di: Fang, Qingkai, et al.
  Pubblicazione: (2024)
• LLaMA-Omni: Seamless Speech Interaction with Large Language Models
  di: Fang, Qingkai, et al.
  Pubblicazione: (2024)
• Effectiveness of Text, Acoustic, and Lattice-based representations in Spoken Language Understanding tasks
  di: Villatoro-Tello, Esaú, et al.
  Pubblicazione: (2022)
• SW-ASR: A Context-Aware Hybrid ASR Pipeline for Robust Single Word Speech Recognition
  di: Sharma, Manali, et al.
  Pubblicazione: (2026)