Wenxuan Wu, Xueyuan Chen, Shuai Wang 0016, Jiadong Wang, Lingwei Meng, Xixin Wu, Helen Meng, Haizhou Li 0001. $C^{2}$AV-TSE: Context and Confidence-Aware Audio Visual Target Speaker Extraction. J. Sel. Topics Signal Processing, 19(4):646-657, May 2025. [doi]
Abstract is missing.