@article{speechclipselfsupervisedmultitask,
  title = {SpeechCLIP+: Self-supervised multi-task representation learning for speech via CLIP and speech-image data},
  author = {Hsuan-Fu Wang and Yi-Jen Shih and Heng-Jui Chang and Layne Berry and Puyuan Peng and Hung-Yi Lee and Hsin-Min Wang and David Harwath},
  year = {2024},
  eprint = {2402.06959},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.06959v1},
}