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

Understand

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.