mlsanityData to 14 Oct 2026

The USTC-NELSLIP Systems for Simultaneous Speech Translation Task at IWSLT 2021

arXiv 2107.00279 ↗First posted 1 Jul 2021cs.CL cs.SD eess.AScited by 13

Not on the map. Why?

Abstract (arXiv)

This paper describes USTC-NELSLIP's submissions to the IWSLT2021 Simultaneous Speech Translation task. We proposed a novel simultaneous translation model, Cross Attention Augmented Transducer (CAAT), which extends conventional RNN-T to sequence-to-sequence tasks without monotonic constraints, e.g., simultaneous translation. Experiments on speech-to-text (S2T) and text-to-text (T2T) simultaneous translation tasks shows CAAT achieves better quality-latency trade-offs compared to textitwait-k, one of the previous state-of-the-art approaches. Based on CAAT architecture and data augmentation, we build S2T and T2T simultaneous translation systems in this evaluation campaign. Compared to last year's optimal systems, our S2T simultaneous translation system improves by an average of 11.3 BLEU for all latency regimes, and our T2T simultaneous translation system improves by an average of 4.6 BLEU.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 20 of its 28 references that are in the map. First posted on arXiv 1 Jul 2021.

Builds on

20 of 28 references.

References · 20

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  3. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,989
  4. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,488
  5. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,380
  6. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 804
  7. 2016Sequence-Level Knowledge Distillationcited by 801
  8. 2019Revisiting Self-Training for Neural Sequence Generationcited by 155
  9. 2019Monotonic Infinite Lookback Attention for Simultaneous Machine Translationcited by 104
  10. 2016Learning to Translate in Real-time with Neural Machine Translationcited by 97
  11. 2020SimulEval: An Evaluation Toolkit for Simultaneous Translationcited by 94
  12. 2019Monotonic Multihead Attentioncited by 93
8 more
  1. 2019End-to-End Speech Translation with Knowledge Distillationcited by 58
  2. 2019Almost Unsupervised Text to Speech and Automatic Speech Recognitioncited by 41
  3. 2020Self-Training for End-to-End Speech Translationcited by 36
  4. 2020Streaming Transformer-based Acoustic Models Using Self-attention with Augmented Memorycited by 35
  5. 2019Self-Attention Aligner: A Latency-Control End-to-End Model for ASR Using Self-Attention Network and Chunk-Hoppingcited by 33
  6. 2019Simultaneous Translation with Flexible Policy via Restricted Imitation Learningcited by 22
  7. 2019Speculative Beam Search for Simultaneous Translationcited by 10
  8. 2020ON-TRAC Consortium for End-to-End and Simultaneous Speech Translation Challenge Tasks at IWSLT 2020cited by 9

Built on by

Cited by year

Citing papers per year: 2022: 5; 2023: 5; 2024: 3.

13 papers.

Sort:

By area:

  1. 2022Attention as a Guide for Simultaneous Speech Translationcited by 32
  2. 2022CUNI-KIT System for Simultaneous Speech Translation Task at IWSLT 2022cited by 30
  3. 2022Does Simultaneous Speech Translation need Simultaneous Models?cited by 22
  4. 2024GenTranslate: Large Language Models are Generative Multilingual Speech and Machine Translatorscited by 22
  5. 2024How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?cited by 17
  6. 2022Improving Simultaneous Machine Translation with Monolingual Datacited by 13
  7. 2023Metric-oriented Speech Enhancement using Diffusion Probabilistic Modelcited by 11
  8. 2023Unifying Speech Enhancement and Separation with Gradient Modulation for End-to-End Noise-Robust Speech Separationcited by 10
  9. 2023Gradient Remedy for Multi-Task Learning in End-to-End Noise-Robust Speech Recognitioncited by 10
  10. 2023Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognitioncited by 9
  11. 2023Direct Models for Simultaneous Translation and Automatic Subtitling: FBK@IWSLT2023cited by 6
  12. 2022Multilingual Simultaneous Speech Translationcited by 2
1 more
  1. 2024R-BI: Regularized Batched Inputs enhance Incremental Decoding Framework for Low-Latency Simultaneous Speech Translationcited by 1