Query-Based Asymmetric Modeling with Decoupled Input-Output Rates for Speech Restoration

Documenti analoghi

• Asymmetric Encoder-Decoder Based on Time-Frequency Correlation for Speech Separation
  di: Shin, Ui-Hyeop, et al.
  Pubblicazione: (2026)
• Stack Less, Repeat More: A Block Reusing Approach for Progressive Speech Enhancement
  di: Kim, Jangyeon, et al.
  Pubblicazione: (2025)
• Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation
  di: Shin, Ui-Hyeop, et al.
  Pubblicazione: (2024)
• Statistical Beamformer Exploiting Non-stationarity and Sparsity with Spatially Constrained ICA for Robust Speech Recognition
  di: Shin, Ui-Hyeop, et al.
  Pubblicazione: (2023)
• TF-CorrNet: Leveraging Spatial Correlation for Continuous Speech Separation
  di: Shin, Ui-Hyeop, et al.
  Pubblicazione: (2025)