# M3ST: Mix at Three Levels for Speech Translation

arXiv: https://arxiv.org/abs/2212.03657 · HTML: https://mlsanity.com/paper/2212.03657/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 26 references that are in the map.
- First posted on arXiv 7 Dec 2022.

## Builds on (most cited first, 19 of 19)

- [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)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation](https://mlsanity.com/paper/2004.11867/) (2020)
- [fairseq S2T: Fast Speech-to-Text Modeling with fairseq](https://mlsanity.com/paper/2010.05171/) (2020)
- [Cross-modal Contrastive Learning for Speech Translation](https://mlsanity.com/paper/2205.02444/) (2022)
- [STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation](https://mlsanity.com/paper/2203.10426/) (2022)
- [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)
- [End-to-end Speech Translation via Cross-modal Progressive Training](https://mlsanity.com/paper/2104.10380/) (2021)
- [MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognition](https://mlsanity.com/paper/2102.12664/) (2021)
- [Sample, Translate, Recombine: Leveraging Audio Alignments for Data Augmentation in End-to-end Speech Translation](https://mlsanity.com/paper/2203.08757/) (2022)
- [Revisiting End-to-End Speech-to-Text Translation From Scratch](https://mlsanity.com/paper/2206.04571/) (2022)
- [GigaST: A 10,000-hour Pseudo Speech Translation Corpus](https://mlsanity.com/paper/2204.03939/) (2022)
- [Regularizing End-to-End Speech Translation with Triangular Decomposition Agreement](https://mlsanity.com/paper/2112.10991/) (2021)
- [SkinAugment: Auto-Encoding Speaker Conversions for Automatic Speech Translation](https://mlsanity.com/paper/2002.12231/) (2020)

## Built on by (most cited first, 21 of 21)

- [Implicit Neural Representation for Cooperative Low-light Image Enhancement](https://mlsanity.com/paper/2303.11722/) (2023)
- [CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image Steganography](https://mlsanity.com/paper/2305.16936/) (2023)
- [Enhancing Dialogue State Tracking Models through LLM-backed User-Agents Simulation](https://mlsanity.com/paper/2405.13037/) (2024)
- [DUB: Discrete Unit Back-translation for Speech Translation](https://mlsanity.com/paper/2305.11411/) (2023)
- [PoseRAC: Pose Saliency Transformer for Repetitive Action Counting](https://mlsanity.com/paper/2303.08450/) (2023)
- [A Frustratingly Easy Plug-and-Play Detection-and-Reasoning Module for Chinese Spelling Check](https://mlsanity.com/paper/2310.09119/) (2023)
- [ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation](https://mlsanity.com/paper/2305.14838/) (2023)
- [CTC-based Non-autoregressive Speech Translation](https://mlsanity.com/paper/2305.17358/) (2023)
- [Tuning Large language model for End-to-end Speech Translation](https://mlsanity.com/paper/2310.02050/) (2023)
- [FiTs: Fine-grained Two-stage Training for Knowledge-aware Question Answering](https://mlsanity.com/paper/2302.11799/) (2023)
- [Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learning](https://mlsanity.com/paper/2305.18158/) (2023)
- [MOSPC: MOS Prediction Based on Pairwise Comparison](https://mlsanity.com/paper/2306.10493/) (2023)
- [Modality Adaption or Regularization? A Case Study on End-to-End Speech Translation](https://mlsanity.com/paper/2306.07650/) (2023)
- [An Empirical Study of Consistency Regularization for End-to-End Speech-to-Text Translation](https://mlsanity.com/paper/2308.14482/) (2023)
- [Rethinking and Improving Multi-task Learning for End-to-end Speech Translation](https://mlsanity.com/paper/2311.03810/) (2023)
- [ML-LMCL: Mutual Learning and Large-Margin Contrastive Learning for Improving ASR Robustness in Spoken Language Understanding](https://mlsanity.com/paper/2311.11375/) (2023)
- [CLEME: Debiasing Multi-reference Evaluation for Grammatical Error Correction](https://mlsanity.com/paper/2305.10819/) (2023)
- [Cross-Modal Multi-Tasking for Speech-to-Text Translation via Hard Parameter Sharing](https://mlsanity.com/paper/2309.15826/) (2023)
- [Bridging the Gaps of Both Modality and Language: Synchronous Bilingual CTC for Speech Translation and Speech Recognition](https://mlsanity.com/paper/2309.12234/) (2023)
- [I2KD-SLU: An Intra-Inter Knowledge Distillation Framework for Zero-Shot Cross-Lingual Spoken Language Understanding](https://mlsanity.com/paper/2310.02594/) (2023)
- [Revisiting Interpolation Augmentation for Speech-to-Text Generation](https://mlsanity.com/paper/2406.15846/) (2024)

## Abstract (arXiv)

How to solve the data scarcity problem for end-to-end speech-to-text translation (ST)? It's well known that data augmentation is an efficient method to improve performance for many tasks by enlarging the dataset. In this paper, we propose Mix at three levels for Speech Translation (M^3ST) method to increase the diversity of the augmented training corpus. Specifically, we conduct two phases of fine-tuning based on a pre-trained model using external machine translation (MT) data. In the first stage of fine-tuning, we mix the training corpus at three levels, including word level, sentence level and frame level, and fine-tune the entire model with mixed data. At the second stage of fine-tuning, we take both original speech sequences and original text sequences in parallel into the model to fine-tune the network, and use Jensen-Shannon divergence to regularize their outputs. Experiments on MuST-C speech translation benchmark and analysis show that M^3ST outperforms current strong baselines and achieves state-of-the-art results on eight directions with an average BLEU of 29.9.