# Source and Target Bidirectional Knowledge Distillation for End-to-end Speech Translation

arXiv: https://arxiv.org/abs/2104.06457 · HTML: https://mlsanity.com/paper/2104.06457/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Placed in Speech and audio distillation, one of 12 directions in Knowledge distillation.
- Builds on 40 of its 57 references that are in the map.
- First posted on arXiv 13 Apr 2021.

## Placed in

- Knowledge distillation / [Speech and audio distillation](https://mlsanity.com/distill/speech-and-audio-distillation/)

## Builds on (most cited first, 30 of 40)

- [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)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [Sequence-Level Knowledge Distillation](https://mlsanity.com/paper/1606.07947/) (2016)
- [Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates](https://mlsanity.com/paper/1804.10959/) (2018)
- [Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/1711.02281/) (2017)
- [A Comparative Study on Transformer vs RNN in Speech Applications](https://mlsanity.com/paper/1909.06317/) (2019)
- [fairseq S2T: Fast Speech-to-Text Modeling with fairseq](https://mlsanity.com/paper/2010.05171/) (2020)
- [Understanding Knowledge Distillation in Non-autoregressive Machine Translation](https://mlsanity.com/paper/1911.02727/) (2019)
- [Sequence-to-Sequence Models Can Directly Translate Foreign Speech](https://mlsanity.com/paper/1703.08581/) (2017)
- [Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasing](https://mlsanity.com/paper/2004.14564/) (2020)
- [Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation](https://mlsanity.com/paper/1612.01744/) (2016)
- [ESPnet-ST: All-in-One Speech Translation Toolkit](https://mlsanity.com/paper/2004.10234/) (2020)
- [CoVoST 2 and Massively Multilingual Speech-to-Text Translation](https://mlsanity.com/paper/2007.10310/) (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)
- [End-to-End Speech Translation with Knowledge Distillation](https://mlsanity.com/paper/1904.08075/) (2019)
- [Curriculum Pre-training for End-to-End Speech Translation](https://mlsanity.com/paper/2004.10093/) (2020)
- [Understanding and Improving Lexical Choice in Non-Autoregressive Translation](https://mlsanity.com/paper/2012.14583/) (2020)
- [Tied Multitask Learning for Neural Speech Translation](https://mlsanity.com/paper/1802.06655/) (2018)
- [Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation](https://mlsanity.com/paper/2011.00747/) (2020)
- [ParaNMT-50M: Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations](https://mlsanity.com/paper/1711.05732/) (2017)
- [A Comparative Study on End-to-end Speech to Text Translation](https://mlsanity.com/paper/1911.08870/) (2019)
- [Bridging the Gap between Pre-Training and Fine-Tuning for End-to-End Speech Translation](https://mlsanity.com/paper/1909.07575/) (2019)
- [ParaBank: Monolingual Bitext Generation and Sentential Paraphrasing via Lexically-constrained Neural Machine Translation](https://mlsanity.com/paper/1901.03644/) (2019)

## Built on by (most cited first, 28 of 28)

- [Cross-modal Contrastive Learning for Speech Translation](https://mlsanity.com/paper/2205.02444/) (2022)
- [UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Units](https://mlsanity.com/paper/2212.08055/) (2022)
- [STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation](https://mlsanity.com/paper/2203.10426/) (2022)
- [Sample, Translate, Recombine: Leveraging Audio Alignments for Data Augmentation in End-to-end Speech Translation](https://mlsanity.com/paper/2203.08757/) (2022)
- [Pre-training for Speech Translation: CTC Meets Optimal Transport](https://mlsanity.com/paper/2301.11716/) (2023)
- [CMOT: Cross-modal Mixup via Optimal Transport for Speech Translation](https://mlsanity.com/paper/2305.14635/) (2023)
- [Understanding and Bridging the Modality Gap for Speech Translation](https://mlsanity.com/paper/2305.08706/) (2023)
- [Recent Advances in Direct Speech-to-text Translation](https://mlsanity.com/paper/2306.11646/) (2023)
- [Efficient yet Competitive Speech Translation: FBK@IWSLT2022](https://mlsanity.com/paper/2205.02629/) (2022)
- [ESPnet-ST-v2: Multipurpose Spoken Language Translation Toolkit](https://mlsanity.com/paper/2304.04596/) (2023)
- [Non-autoregressive End-to-end Speech Translation with Parallel Autoregressive Rescoring](https://mlsanity.com/paper/2109.04411/) (2021)
- [Fast-MD: Fast Multi-Decoder End-to-End Speech Translation with Non-Autoregressive Hidden Intermediates](https://mlsanity.com/paper/2109.12804/) (2021)
- [ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation](https://mlsanity.com/paper/2305.14838/) (2023)
- [Tuning Large language model for End-to-end Speech Translation](https://mlsanity.com/paper/2310.02050/) (2023)
- [Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation](https://mlsanity.com/paper/2210.09556/) (2022)
- [Make More of Your Data: Minimal Effort Data Augmentation for Automatic Speech Recognition and Translation](https://mlsanity.com/paper/2210.15398/) (2022)
- [An Empirical Study of Consistency Regularization for End-to-End Speech-to-Text Translation](https://mlsanity.com/paper/2308.14482/) (2023)
- [Generating Synthetic Speech from SpokenVocab for Speech Translation](https://mlsanity.com/paper/2210.08174/) (2022)
- [Duplex Diffusion Models Improve Speech-to-Speech Translation](https://mlsanity.com/paper/2305.12628/) (2023)
- [Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison](https://mlsanity.com/paper/2501.02370/) (2025)
- [Two-Pass End-to-End ASR Model Compression](https://mlsanity.com/paper/2201.02741/) (2022)
- [Improving speech translation by fusing speech and text](https://mlsanity.com/paper/2305.14042/) (2023)
- [Cross-Modal Multi-Tasking for Speech-to-Text Translation via Hard Parameter Sharing](https://mlsanity.com/paper/2309.15826/) (2023)
- [Sentence-wise Speech Summarization: Task, Datasets, and End-to-End Modeling with LM Knowledge Distillation](https://mlsanity.com/paper/2408.00205/) (2024)
- [Compact Speech Translation Models via Discrete Speech Units Pretraining](https://mlsanity.com/paper/2402.19333/) (2024)
- [ESPnet-ST IWSLT 2021 Offline Speech Translation System](https://mlsanity.com/paper/2107.00636/) (2021)
- [Cross-Modal Robustness Transfer (CMRT): Training Robust Speech Translation Models Using Adversarial Text](https://mlsanity.com/paper/2602.11933/) (2026)
- [Align, Integrate, and Fire: Efficient Token-Level Alignment for Zero-Shot SpeechLLMs](https://mlsanity.com/paper/2609.18516/) (2026)

## Abstract (arXiv)

A conventional approach to improving the performance of end-to-end speech translation (E2E-ST) models is to leverage the source transcription via pre-training and joint training with automatic speech recognition (ASR) and neural machine translation (NMT) tasks. However, since the input modalities are different, it is difficult to leverage source language text successfully. In this work, we focus on sequence-level knowledge distillation (SeqKD) from external text-based NMT models. To leverage the full potential of the source language information, we propose backward SeqKD, SeqKD from a target-to-source backward NMT model. To this end, we train a bilingual E2E-ST model to predict paraphrased transcriptions as an auxiliary task with a single decoder. The paraphrases are generated from the translations in bitext via back-translation. We further propose bidirectional SeqKD in which SeqKD from both forward and backward NMT models is combined. Experimental evaluations on both autoregressive and non-autoregressive models show that SeqKD in each direction consistently improves the translation performance, and the effectiveness is complementary regardless of the model capacity.