Enroll-on-Wakeup: A First Comparative Study of Target Speech Extraction for Seamless Interaction in Real Noisy Human-Machine Dialogue Scenarios

Documenti analoghi

• Unified Architecture and Unsupervised Speech Disentanglement for Speaker Embedding-Free Enrollment in Personalized Speech Enhancement
  di: Huang, Ziling, et al.
  Pubblicazione: (2025)
• SEF-PNet: Speaker Encoder-Free Personalized Speech Enhancement with Local and Global Contexts Aggregation
  di: Huang, Ziling, et al.
  Pubblicazione: (2025)
• Noisy Disentanglement with Tri-stage Training for Noise-Robust Speech Recognition
  di: Chen, Shuangyuan, et al.
  Pubblicazione: (2025)
• Study of Lightweight Transformer Architectures for Single-Channel Speech Enhancement
  di: Zhao, Haixin, et al.
  Pubblicazione: (2025)
• Continual Test-time Adaptation for End-to-end Speech Recognition on Noisy Speech
  di: Lin, Guan-Ting, et al.
  Pubblicazione: (2024)