AAAI 2023technical14 citations
Improving End-to-End Speech Translation by Leveraging Auxiliary Speech and Text Data
Yuhao Zhang, Chen Xu, Bojie Hu, Chunliang Zhang, Tong Xiao, Jingbo Zhu
Abstract
We present a method for introducing a text encoder into pre-trained end-to-end speech translation systems. It enhances the ability of adapting one modality (i.e., source-language speech) to another (i.e., source-language text). Thus, the speech translation model can learn from both unlabeled and labeled data, especially when the source-language text data is abundant. Beyond this, we present a denoising method to build a robust text encoder that can deal with both normal and noisy text data. Our system sets new state-of-the-arts on the MuST-C En-De, En-Fr, and LibriSpeech En-Fr tasks.
BibTeX
@article{Zhang_Xu_Hu_Zhang_Xiao_Zhu_2023, title={Improving End-to-End Speech Translation by Leveraging Auxiliary Speech and Text Data}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/26637}, DOI={10.1609/aaai.v37i11.26637}, abstractNote={We present a method for introducing a text encoder into pre-trained end-to-end speech translation systems. It enhances the ability of adapting one modality (i.e., source-language speech) to another (i.e., source-language text). Thus, the speech translation model can learn from both unlabeled and labeled data, especially when the source-language text data is abundant. Beyond this, we present a denoising method to build a robust text encoder that can deal with both normal and noisy text data. Our system sets new state-of-the-arts on the MuST-C En-De, En-Fr, and LibriSpeech En-Fr tasks.}, number={11}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Zhang, Yuhao and Xu, Chen and Hu, Bojie and Zhang, Chunliang and Xiao, Tong and Zhu, Jingbo}, year={2023}, month={Jun.}, pages={13984-13992} }