@inproceedings{audiotokenadaptationoftextconditioned1,
  title = {AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation},
  author = {Guy Yariv and Itai Gat and Lior Wolf and Yossi Adi and Idan Schwartz},
  year = {2023},
  booktitle = {Interspeech 2023 5},
  eprint = {2305.13050},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2305.13050v1},
}