Conference paper Open Access

Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training

Cheng, Qiao; Fan, Meiyuan; Han, Yaqian; Huang, Jin; Duan, Yitao


Citation Style Language JSON Export

{
  "publisher": "Zenodo", 
  "DOI": "10.5281/zenodo.3524969", 
  "title": "Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training", 
  "issued": {
    "date-parts": [
      [
        2019, 
        11, 
        2
      ]
    ]
  }, 
  "abstract": "<p>In a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard machine translation system is usually trained on parallel corpus composed of clean text and will perform poorly on text with recognition noise, a gap well known in speech translation community. In this paper, we propose a training architecture which aims at making a neural machine translation model more robust against speech recognition errors. Our approach addresses the encoder and the decoder simultaneously using adversarial learning and data augmentation, respectively. Experimental results on IWSLT2018 speech translation task show that our approach can bridge the gap between the ASR output and the MT input, outperforms the baseline by up to 2.83 BLEU on noisy ASR output, while maintaining close performance on clean text.</p>", 
  "author": [
    {
      "family": "Cheng, Qiao"
    }, 
    {
      "family": "Fan, Meiyuan"
    }, 
    {
      "family": "Han, Yaqian"
    }, 
    {
      "family": "Huang, Jin"
    }, 
    {
      "family": "Duan, Yitao"
    }
  ], 
  "type": "paper-conference", 
  "id": "3524969"
}
136
112
views
downloads
All versions This version
Views 136137
Downloads 112112
Data volume 44.8 MB44.8 MB
Unique views 120121
Unique downloads 9696

Share

Cite as