The NiuTrans End-to-End Speech Translation System for IWSLT 2021 Offline Task
Not on the map. Why?
Abstract (arXiv)
This paper describes the submission of the NiuTrans end-to-end speech translation system for the IWSLT 2021 offline task, which translates from the English audio to German text directly without intermediate transcription. We use the Transformer-based model architecture and enhance it by Conformer, relative position encoding, and stacked acoustic and textual encoding. To augment the training data, the English transcriptions are translated to German translations. Finally, we employ ensemble decoding to integrate the predictions from several models trained with the different datasets. Combining these techniques, we achieve 33.84 BLEU points on the MuST-C En-De test set, which shows the enormous potential of the end-to-end model.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 20 of its 34 references that are in the map. First posted on arXiv 6 Jul 2021.
Builds on
20 of 34 references.
References · 20
- 2017Attention Is All You Needcited by 59,932
- 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
- 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
- 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
- 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
- 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
- 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
- 2018Self-Attention with Relative Position Representationscited by 1,112
- 2016Sequence-Level Knowledge Distillationcited by 761
- 2019Learning Deep Transformer Models for Machine Translationcited by 309
- 2017Sequence-to-Sequence Models Can Directly Translate Foreign Speechcited by 121
- 2019Europarl-ST: A Multilingual Corpus For Speech Translation Of Parliamentary Debatescited by 114
8 more
- 2016Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translationcited by 113
- 2020CoVoST 2 and Massively Multilingual Speech-to-Text Translationcited by 73
- 2021Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoderscited by 48
- 2019A Comparative Study on End-to-end Speech to Text Translationcited by 40
- 2020Shallow-to-Deep Training for Neural Machine Translationcited by 36
- 2020End-to-End Speech-Translation with Knowledge Distillation: FBK@IWSLT2020cited by 31
- 2020Relative Positional Encoding for Speech Recognition and Direct Translationcited by 23
- 2020Learning Light-Weight Translation Models from Deep Transformercited by 22
Built on by
Citing papers per year: 2022: 1.
1 paper.