Model Description
This model is designed to address catastrophic forgetting in spoken language models during end-to-end training. It leverages innovative mitigation strategies to enhance model retention and performance over time. For more details, please refer to the paper by Hsiao et al. (2025) here.
Model Usage
To use this model, please check the GitHub repository for installation instructions, example code, and detailed usage guidelines. Ensure you have the required dependencies installed.
Citation
If you use this model in your research or applications, please cite it as follows:
APA: Hsiao, C.-Y., Lu, K.-H., Chang, K.-W., Yang, C.-K., Chen, W.-C., & Lee, H.-y. (2025). Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models. arXiv. https://arxiv.org/abs/2505.17496
BibTeX:
@misc{hsiao2025analyzingmitigationstrategiescatastrophic,
title={Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models},
author={Chi-Yuan Hsiao and Ke-Han Lu and Kai-Wei Chang and Chih-Kai Yang and Wei-Chih Chen and Hung-yi Lee},
year={2025},
eprint={2505.17496},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2505.17496},
}