- Spoken conversation question answering benchmark dataset is from BaiduDisk, the password is 5s6r. More deatils of this dataset can be found at: NAACL 2022 Paper "End-to-end Spoken Conversational Question Answering: Task, Dataset and Model".
If you found this code/work to be useful in your own research, please considering citing the following:
@inproceedings{you2022end,
title={End-to-end Spoken Conversational Question Answering: Task, Dataset and Model},
author={You, Chenyu and Chen, Nuo and Liu, Fenglin and Ge, Shen and Wu, Xian and Zou, Yuexian},
booktitle={Findings of the Association for Computational Linguistics: NAACL 2022},
year={2022},
}
@inproceedings{you2021mrd,
title={MRD-Net: Multi-Modal Residual Knowledge Distillation for Spoken Question Answering.},
author={You, Chenyu and Chen, Nuo and Zou, Yuexian},
booktitle={IJCAI},
year={2021}
}
@inproceedings{you2022selfsupervised,
title={Self-supervised Contrastive Cross-Modality Representation Learning for Spoken Question Answering},
author={You, Chenyu and Chen, Nuo and Zou, Yuexian},
booktitle={Findings of the Association for Computational Linguistics: EMNLP 2021},
year={2021},
}
@inproceedings{you2020contextualized,
title={Contextualized attention-based knowledge transfer for spoken conversational question answering},
author={You, Chenyu and Chen, Nuo and Zou, Yuexian},
booktitle={INTERSPEECH},
year={2021}
}
@inproceedings{you2021knowledge,
title={Knowledge distillation for improved accuracy in spoken question answering},
author={You, Chenyu and Chen, Nuo and Zou, Yuexian},
booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
year={2021}
}
If you have any questions, please contact [email protected].