Self-Training for End-to-End Speech Translation
arXiv:2006.02490
Abstract
One of the main challenges for end-to-end speech translation is data scarcity. We leverage pseudo-labels generated from unlabeled audio by a cascade and an end-to-end speech translation model. This provides 8.3 and 5.7 BLEU gains over a strong semi-supervised baseline on the MuST-C English-French and English-German datasets, reaching state-of-the art performance. The effect of the quality of the pseudo-labels is investigated. Our approach is shown to be more effective than simply pre-training the encoder on the speech recognition task. Finally, we demonstrate the effectiveness of self-training by directly generating pseudo-labels with an end-to-end model instead of a cascade model.
arXiv commentINTERSPEECH 2020
References in corpus (8)
- Libri-Light: A Benchmark for ASR with Limited or No Supervision
- Billion-scale semi-supervised learning for image classification
- Self-Training for End-to-End Speech Recognition
- wav2letter++: The Fastest Open-source Speech Recognition System
- End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures
- Transformers with convolutional context for ASR
- Accelerating Neural Transformer via an Average Attention Network
- CoVoST: A Diverse Multilingual Speech-To-Text Translation Corpus