@inproceedings{kolluri2026card, author = {Kolluri, G.P.K.B. and Zhang, Y. and Kampouridis, M. and Shekhar, R.}, title = {{CARD: Cross-component Audio Representation Distillation for Encoder-Free Audio Captioning}}, booktitle = {IEEE Spoken Language Technology SLT 2026}, publisher = {IEEE}, year = {2026}, doi = {10.48550/arxiv.2607.04619}, url = {https://repository.essex.ac.uk/43881/1/CARD.pdf}, }