An Empirical Study of End-To-End Simultaneous Speech Translation Decoding Strategies
Open Access
- 6 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7528-7532
Abstract
This paper proposes a decoding strategy for end-to-end simultaneous speech translation. We leverage end-to-end models trained in offline mode and conduct an empirical study for two language pairs (English-to-German and English-to-Portuguese). We also investigate different output token granularities including characters and Byte Pair Encoding (BPE) units. The results show that the proposed decoding approach allows to control BLEU/Average Lagging trade-off along different latency regimes. Our best decoding settings achieve comparable results with a strong cascade model evaluated on the simultaneous translation track of IWSLT 2020 shared task.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Efficient Wait-k Models for Simultaneous Machine Translation2020
- Europarl-ST: A Multilingual Corpus for Speech Translation of Parliamentary Debates2020
- End-to-End Simultaneous Translation System for IWSLT2020 Using Modality Agnostic Meta-Learning2020
- FINDINGS OF THE IWSLT 2020 EVALUATION CAMPAIGN2020
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition2019
- Monotonic Infinite Lookback Attention for Simultaneous Machine Translation2019
- STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework2019
- Low-Latency Neural Speech Translation2018
- Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translation2018
- Long Short-Term MemoryNeural Computation, 1997