# Unveiling the Role of Pretraining in Direct Speech Translation

arXiv: https://arxiv.org/abs/2409.18044 · HTML: https://mlsanity.com/paper/2409.18044/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 21 references that are in the map.
- First posted on arXiv 26 Sep 2024.

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [fairseq S2T: Fast Speech-to-Text Modeling with fairseq](https://mlsanity.com/paper/2010.05171/) (2020)
- [Pre-training on high-resource speech recognition improves low-resource speech-to-text translation](https://mlsanity.com/paper/1809.01431/) (2018)
- [End-to-End Automatic Speech Translation of Audiobooks](https://mlsanity.com/paper/1802.04200/) (2018)
- [Measuring the Mixing of Contextual Information in the Transformer](https://mlsanity.com/paper/2203.04212/) (2022)
- [Curriculum Pre-training for End-to-End Speech Translation](https://mlsanity.com/paper/2004.10093/) (2020)
- [Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders](https://mlsanity.com/paper/2105.05752/) (2021)
- [Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer](https://mlsanity.com/paper/2205.11631/) (2022)
- [Pre-training for Speech Translation: CTC Meets Optimal Transport](https://mlsanity.com/paper/2301.11716/) (2023)
- [Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMT](https://mlsanity.com/paper/2109.01396/) (2021)
- [On the Locality of Attention in Direct Speech Translation](https://mlsanity.com/paper/2204.09028/) (2022)

## Built on by (most cited first, 2 of 2)

- [You Are What You Train: Effects of Data Composition on Training Context-aware Machine Translation Models](https://mlsanity.com/paper/2509.14031/) (2025)
- [CAFE: Confining Feature Distillation to Language-Routed Adapters for Compact Multilingual Automatic Speech Recognition](https://mlsanity.com/paper/2610.19134/) (2026)

## Abstract (arXiv)

Direct speech-to-text translation systems encounter an important drawback in data scarcity. A common solution consists on pretraining the encoder on automatic speech recognition, hence losing efficiency in the training process. In this study, we compare the training dynamics of a system using a pretrained encoder, the conventional approach, and one trained from scratch. We observe that, throughout the training, the randomly initialized model struggles to incorporate information from the speech inputs for its predictions. Hence, we hypothesize that this issue stems from the difficulty of effectively training an encoder for direct speech translation. While a model trained from scratch needs to learn acoustic and semantic modeling simultaneously, a pretrained one can just focus on the latter. Based on these findings, we propose a subtle change in the decoder cross-attention to integrate source information from earlier steps in training. We show that with this change, the model trained from scratch can achieve comparable performance to the pretrained one, while reducing the training time.