Introduction to Transformers: an NLP Perspective
Transformers have dominated empirical machine learning models of natural language
processing. In this paper, we introduce basic concepts of Transformers and present key …
processing. In this paper, we introduce basic concepts of Transformers and present key …
Rethinking and improving multi-task learning for end-to-end speech translation
Significant improvements in end-to-end speech translation (ST) have been achieved
through the application of multi-task learning. However, the extent to which auxiliary tasks …
through the application of multi-task learning. However, the extent to which auxiliary tasks …
Soft Alignment of Modality Space for End-to-End Speech Translation
End-to-end Speech Translation (ST) aims to convert speech into target text within a unified
model. The inherent differences between speech and text modalities often impede effective …
model. The inherent differences between speech and text modalities often impede effective …
Efficient Speech-to-Text Translation: Progressive Pruning for Accelerated Speech Pre-trained Model
Recently, speech pre-trained models based on the Transformer architecture have become
very popular for speech-to-text translation tasks. However, computing representation outputs …
very popular for speech-to-text translation tasks. However, computing representation outputs …
Improving End-to-End Speech Translation with Progressive Dual Encoding
In end-to-end speech translation (E2E ST), multi-task learning is often applied due to the
scarcity of labeled ST data. However, the modality gap between speech and source text …
scarcity of labeled ST data. However, the modality gap between speech and source text …