@article{accommodatingaudiomodalityinclipfor, title = {Accommodating Audio Modality in CLIP for Multimodal Processing}, author = {Ludan Ruan and Anwen Hu and Yuqing Song and Liang Zhang and Sipeng Zheng and Qin Jin}, year = {2023}, eprint = {2303.06591}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2303.06591v1}, }