Fine-tuning on Clean Data for End-to-End Speech Translation: FBK @ IWSLT 2018

Mattia Antonino Di Gangi, Roberto Dessì, Roldano Cattoni, Matteo Negri, Marco Turchi


Abstract
This paper describes FBK’s submission to the end-to-end English-German speech translation task at IWSLT 2018. Our system relies on a state-of-the-art model based on LSTMs and CNNs, where the CNNs are used to reduce the temporal dimension of the audio input, which is in general much higher than machine translation input. Our model was trained only on the audio-to-text parallel data released for the task, and fine-tuned on cleaned subsets of the original training corpus. The addition of weight normalization and label smoothing improved the baseline system by 1.0 BLEU point on our validation set. The final submission also featured checkpoint averaging within a training run and ensemble decoding of models trained during multiple runs. On test data, our best single model obtained a BLEU score of 9.7, while the ensemble obtained a BLEU score of 10.24.
Anthology ID:
2018.iwslt-1.22
Volume:
Proceedings of the 15th International Conference on Spoken Language Translation
Month:
October 29-30
Year:
2018
Address:
Brussels
Venues:
EMNLP | IWSLT
SIG:
SIGSLT
Publisher:
International Conference on Spoken Language Translation
Note:
Pages:
147–152
Language:
URL:
https://aclanthology.org/2018.iwslt-1.22
DOI:
Bibkey:
Cite (ACL):
Mattia Antonino Di Gangi, Roberto Dessì, Roldano Cattoni, Matteo Negri, and Marco Turchi. 2018. Fine-tuning on Clean Data for End-to-End Speech Translation: FBK @ IWSLT 2018. In Proceedings of the 15th International Conference on Spoken Language Translation, pages 147–152, Brussels. International Conference on Spoken Language Translation.
Cite (Informal):
Fine-tuning on Clean Data for End-to-End Speech Translation: FBK @ IWSLT 2018 (Di Gangi et al., IWSLT 2018)
Copy Citation:
PDF:
https://aclanthology.org/2018.iwslt-1.22.pdf