@article{ontheeffectsofheterogeneousdatasources, title = {On the Effects of Heterogeneous Data Sources on Speech-to-Text Foundation Models}, author = {Jinchuan Tian and Yifan Peng and William Chen and Kwanghee Choi and Karen Livescu and Shinji Watanabe}, year = {2024}, eprint = {2406.09282}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.09282v1}, }