FBK@IWSLT 2011
N. Ruiz, A. Bisazza, F. Brugnara, D. Falavigna, D. Giuliani, S. Jaber, R. Gretter, M. Federico
Abstract
This paper reports on the participation of FBK at the IWSLT 2011 Evaluation: namely in the English ASR track, the Arabic-English MT track and the English-French MT and SLT tracks. Our ASR system features acoustic models trained on a portion of the TED talk recordings that was automatically selected according to the fidelity of the provided transcriptions. Three decoding steps are performed interleaved by acoustic feature normalization and acoustic model adaptation. Concerning the MT and SLT systems, besides language specific pre-processing and the automatic introduction of punctuation in the ASR output, two major improvements are reported over our last year baselines. First, we applied a fill-up method for phrase-table adaptation; second, we explored the use of hybrid class-based language models to better capture the language style of public speeches.- Anthology ID:
- 2011.iwslt-evaluation.11
- Volume:
- Proceedings of the 8th International Workshop on Spoken Language Translation: Evaluation Campaign
- Month:
- December 8-9
- Year:
- 2011
- Address:
- San Francisco, California
- Editors:
- Marcello Federico, Mei-Yuh Hwang, Margit Rödder, Sebastian Stüker
- Venue:
- IWSLT
- SIG:
- SIGSLT
- Publisher:
- Note:
- Pages:
- 86–93
- Language:
- URL:
- https://aclanthology.org/2011.iwslt-evaluation.11
- DOI:
- Cite (ACL):
- N. Ruiz, A. Bisazza, F. Brugnara, D. Falavigna, D. Giuliani, S. Jaber, R. Gretter, and M. Federico. 2011. FBK@IWSLT 2011. In Proceedings of the 8th International Workshop on Spoken Language Translation: Evaluation Campaign, pages 86–93, San Francisco, California.
- Cite (Informal):
- FBK@IWSLT 2011 (Ruiz et al., IWSLT 2011)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2011.iwslt-evaluation.11.pdf