A dual task learning approach to fine-tune a multilingual semantic speech encoder for Spoken Language Understanding

Documenti analoghi

• Semantic enrichment towards efficient speech representations
  di: Laperrière, Gaëlle, et al.
  Pubblicazione: (2023)
• Distilling a speech and music encoder with task arithmetic
  di: Ritter-Gutierrez, Fabian, et al.
  Pubblicazione: (2025)
• Robust fine-tuning of speech recognition models via model merging: application to disordered speech
  di: Ducorroy, Alexandre, et al.
  Pubblicazione: (2025)
• Towards noise-robust speech inversion through multi-task learning with speech enhancement
  di: Tabatabaee, Saba, et al.
  Pubblicazione: (2026)
• DualSep: A Light-weight dual-encoder convolutional recurrent network for real-time in-car speech separation
  di: Wang, Ziqian, et al.
  Pubblicazione: (2024)