Abstract
End-to-end speech-to-text translation (ST), which directly translates the source language speech to the target language text, has attracted intensive attention recently. However, the combination of speech recognition and machine translation in a single model poses a heavy burden on the direct cross-modal cross-lingual mapping. To reduce the learning difficulty, we propose SDST, an integral framework with \textbf{S}uccessive \textbf{D}ecoding for end-to-end \textbf{S}peech-to-text \textbf{T}ranslation task. This method is verified in two mainstream datasets. Experiments show that our proposed \method improves the previous state-of-the-art methods by big margins.
Abstract (translated)
URL
https://arxiv.org/abs/2009.09737
