X-CrossNet: A complex spectral mapping approach to target speaker extraction with cross attention speaker embedding fusion

Documenti analoghi

• Visual-based spatial audio generation system for multi-speaker environments
  di: Liu, Xiaojing, et al.
  Pubblicazione: (2025)
• Hierarchical speaker representation for target speaker extraction
  di: He, Shulin, et al.
  Pubblicazione: (2022)
• Improving curriculum learning for target speaker extraction with synthetic speakers
  di: Liu, Yun, et al.
  Pubblicazione: (2024)
• Text adaptation for speaker verification with speaker-text factorized embeddings
  di: Yang, Yexin, et al.
  Pubblicazione: (2025)
• An audio-quality-based multi-strategy approach for target speaker extraction in the MISP 2023 Challenge
  di: Han, Runduo, et al.
  Pubblicazione: (2024)