@article{silvarspeechdrivenmultimodalmodelfor,
  title = {SilVar: Speech Driven Multimodal Model for Reasoning Visual Question Answering and Object Localization},
  author = {Tan-Hanh Pham and Hoang-Nam Le and Phu-Vinh Nguyen and Chris Ngo and Truong-Son Hy},
  year = {2024},
  eprint = {2412.16771},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.16771v1},
}