@article{datacentricimprovementsforenhancingmulti, title = {Data-Centric Improvements for Enhancing Multi-Modal Understanding in Spoken Conversation Modeling}, author = {Maximillian Chen and Ruoxi Sun and Sercan Ö. Arik}, year = {2024}, eprint = {2412.15995}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.15995v1}, }