# Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation

arXiv: https://arxiv.org/abs/2210.09556 · HTML: https://mlsanity.com/paper/2210.09556/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 54 references that are in the map.
- First posted on arXiv 18 Oct 2022.

## Builds on (most cited first, 30 of 42)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations](https://mlsanity.com/paper/1910.05453/) (2019)
- [SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing](https://mlsanity.com/paper/2110.07205/) (2021)
- [fairseq S2T: Fast Speech-to-Text Modeling with fairseq](https://mlsanity.com/paper/2010.05171/) (2020)
- [A* Sampling](https://mlsanity.com/paper/1411.0030/) (2014)
- [Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation](https://mlsanity.com/paper/1612.01744/) (2016)
- [mSLAM: Massively multilingual joint pre-training for speech and text](https://mlsanity.com/paper/2202.01374/) (2022)
- [ESPnet-ST: All-in-One Speech Translation Toolkit](https://mlsanity.com/paper/2004.10234/) (2020)
- [Pre-training on high-resource speech recognition improves low-resource speech-to-text translation](https://mlsanity.com/paper/1809.01431/) (2018)
- [SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training](https://mlsanity.com/paper/2110.10329/) (2021)
- [End-to-End Automatic Speech Translation of Audiobooks](https://mlsanity.com/paper/1802.04200/) (2018)
- [End-to-End Speech Translation with Knowledge Distillation](https://mlsanity.com/paper/1904.08075/) (2019)
- [Leveraging Weakly Supervised Data to Improve End-to-End Speech-to-Text Translation](https://mlsanity.com/paper/1811.02050/) (2018)
- [CoVoST: A Diverse Multilingual Speech-To-Text Translation Corpus](https://mlsanity.com/paper/2002.01320/) (2020)
- [Curriculum Pre-training for End-to-End Speech Translation](https://mlsanity.com/paper/2004.10093/) (2020)
- [STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation](https://mlsanity.com/paper/2203.10426/) (2022)
- [Bridging the Modality Gap for Speech-to-Text Translation](https://mlsanity.com/paper/2010.14920/) (2020)
- [Lightweight Adapter Tuning for Multilingual Speech Translation](https://mlsanity.com/paper/2106.01463/) (2021)
- [Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task](https://mlsanity.com/paper/2107.05782/) (2021)
- [A General Multi-Task Learning Framework to Leverage Text Data for Speech to Text Tasks](https://mlsanity.com/paper/2010.11338/) (2020)
- [Learning Shared Semantic Space for Speech-to-Text Translation](https://mlsanity.com/paper/2105.03095/) (2021)
- [Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders](https://mlsanity.com/paper/2105.05752/) (2021)
- [Fused Acoustic and Text Encoding for Multimodal Bilingual Pretraining and Speech Translation](https://mlsanity.com/paper/2102.05766/) (2021)
- [End-to-end Speech Translation via Cross-modal Progressive Training](https://mlsanity.com/paper/2104.10380/) (2021)

## Built on by (most cited first, 6 of 6)

- [WACO: Word-Aligned Contrastive Learning for Speech Translation](https://mlsanity.com/paper/2212.09359/) (2022)
- [MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and Recognition](https://mlsanity.com/paper/2303.05309/) (2023)
- [Pushing the Limits of Zero-shot End-to-End Speech Translation](https://mlsanity.com/paper/2402.10422/) (2024)
- [An Empirical Study of Consistency Regularization for End-to-End Speech-to-Text Translation](https://mlsanity.com/paper/2308.14482/) (2023)
- [Zero-resource Speech Translation and Recognition with LLMs](https://mlsanity.com/paper/2412.18566/) (2024)
- [Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data?](https://mlsanity.com/paper/2406.07289/) (2024)

## Abstract (arXiv)

End-to-end Speech Translation (ST) aims at translating the source language speech into target language text without generating the intermediate transcriptions. However, the training of end-to-end methods relies on parallel ST data, which are difficult and expensive to obtain. Fortunately, the supervised data for automatic speech recognition (ASR) and machine translation (MT) are usually more accessible, making zero-shot speech translation a potential direction. Existing zero-shot methods fail to align the two modalities of speech and text into a shared semantic space, resulting in much worse performance compared to the supervised ST methods. In order to enable zero-shot ST, we propose a novel Discrete Cross-Modal Alignment (DCMA) method that employs a shared discrete vocabulary space to accommodate and match both modalities of speech and text. Specifically, we introduce a vector quantization module to discretize the continuous representations of speech and text into a finite set of virtual tokens, and use ASR data to map corresponding speech and text to the same virtual token in a shared codebook. This way, source language speech can be embedded in the same semantic space as the source language text, which can be then transformed into target language text with an MT module. Experiments on multiple language pairs demonstrate that our zero-shot ST method significantly improves the SOTA, and even performers on par with the strong supervised ST baselines.