Adaptive Multi-Modal Transformer Decoders for Robust Speech and Scene Classification Using Audio– Visual Fusion. International Journal of Engineering Research and Science & Technology, [S. l.], v. 22, n. 1, p. 516–521, 2026. DOI: 10.62643/. Disponível em: https://ijerst.org/index.php/ijerst/article/view/1834. Acesso em: 11 nov. 2026.