Improving speech translation by cross-modal multi-grained contrastive learning
H Zhang, N Si, Y Chen, W Zhang… - … on Audio, Speech …, 2023 - ieeexplore.ieee.org
The end-to-end speech translation (E2E-ST) model has gradually become a mainstream
paradigm due to its low latency and less error propagation. However, it is non-trivial to train …
paradigm due to its low latency and less error propagation. However, it is non-trivial to train …
Adatrans: Adapting with boundary-based shrinking for end-to-end speech translation
To alleviate the data scarcity problem in End-to-end speech translation (ST), pre-training on
data for speech recognition and machine translation is considered as an important …
data for speech recognition and machine translation is considered as an important …