@article{multimodalspeechemotionrecognitionusing1,
  title = {Multimodal Speech Emotion Recognition using Cross Attention with Aligned Audio and Text},
  author = {Yoonhyung Lee and Seunghyun Yoon and Kyomin Jung},
  year = {2022},
  eprint = {2207.12895},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2207.12895v1},
}