The Volctrans Neural Speech Translation System for IWSLT 2021
Not on the map. Why?
Abstract (arXiv)
This paper describes the systems submitted to IWSLT 2021 by the Volctrans team. We participate in the offline speech translation and text-to-text simultaneous translation tracks. For offline speech translation, our best end-to-end model achieves 8.1 BLEU improvements over the benchmark on the MuST-C test set and is even approaching the results of a strong cascade solution. For text-to-text simultaneous translation, we explore the best practice to optimize the wait-k model. As a result, our final submitted systems exceed the benchmark at around 7 BLEU on the same latency regime. We will publish our code and model to facilitate both future research works and industrial applications. This paper describes the systems submitted to IWSLT 2021 by the Volctrans team. We participate in the offline speech translation and text-to-text simultaneous translation tracks. For offline speech translation, our best end-to-end model achieves 7.9 BLEU improvements over the benchmark on the MuST-C test set and is even approaching the results of a strong cascade solution. For text-to-text simultaneous translation, we explore the best practice to optimize the wait-k model. As a result, our final submitted systems exceed the benchmark at around 7 BLEU on the same latency regime. We release our code and model at urlhttps://github.com/bytedance/neurst/tree/master/examples/iwslt21 to facilitate both future research works and industrial applications.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 24 of its 36 references that are in the map. First posted on arXiv 16 May 2021.
Builds on
24 of 36 references.
References · 24
- 2017Attention Is All You Needcited by 59,932
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
- 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
- 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
- 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
- 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
- 2016Sequence-Level Knowledge Distillationcited by 761
- 2018TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptationcited by 224
- 2019Pay Less Attention with Lightweight and Dynamic Convolutionscited by 211
- 2019A Comparative Study on Transformer vs RNN in Speech Applicationscited by 210
- 2020SimulEval: An Evaluation Toolkit for Simultaneous Translationcited by 94
12 more
- 2019Tagged Back-Translationcited by 76
- 2018Pre-training on high-resource speech recognition improves low-resource speech-to-text translationcited by 70
- 2020Efficient Wait-k Models for Simultaneous Machine Translationcited by 59
- 2018Leveraging Weakly Supervised Data to Improve End-to-End Speech-to-Text Translationcited by 57
- 2020Curriculum Pre-training for End-to-End Speech Translationcited by 57
- 2020A General Multi-Task Learning Framework to Leverage Text Data for Speech to Text Taskscited by 51
- 2021End-to-end Speech Translation via Cross-modal Progressive Trainingcited by 47
- 2017Ensemble Distillation for Neural Machine Translationcited by 39
- 2020Self-Training for End-to-End Speech Translationcited by 36
- 2019Analyzing ASR pretraining for low-resource speech-to-text translationcited by 27
- 2020NeurST: Neural Speech Translation Toolkitcited by 23
- 2020The Volctrans Machine Translation System for WMT20cited by 7
Built on by
Citing papers per year: 2022: 2; 2023: 0; 2024: 1.
3 papers.