FBK@IWSLT 2011

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.

[1]  Fabio Brugnara,et al.  Experiments on cross-system acoustic model adaptation , 2007, 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU).

[2]  Stefan Besling,et al.  Language model speaker adaptation , 1995, EUROSPEECH.

[3]  Philip C. Woodland,et al.  Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models , 1995, Comput. Speech Lang..

[4]  Helmut Schmidt,et al.  Probabilistic part-of-speech tagging using decision trees , 1994 .

[5]  Daniel Jurafsky,et al.  Automatic Tagging of Arabic Text: From Raw Text to Base Phrase Chunks , 2004, NAACL.

[6]  Preslav Nakov,et al.  Improving English-Spanish Statistical Machine Translation: Experiments in Domain Adaptation, Sentence Paraphrasing, Tokenization, and Recasing , 2008, WMT@ACL.

[7]  Marcello Federico,et al.  Efficient language model adaptation through MDI estimation , 1999, EUROSPEECH.

[8]  Fabio Brugnara,et al.  Adaptive training using simple target models [speech recognition applications] , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[9]  Christopher D. Manning,et al.  A Simple and Effective Hierarchical Phrase Reordering Model , 2008, EMNLP.

[10]  Mauro Cettolo,et al.  IRSTLM: an open source toolkit for handling large scale language models , 2008, INTERSPEECH.

[11]  Nizar Habash.  REMOOV : A Tool for Online Handling of Out-of-Vocabulary Words in Machine Translation , 2009 .

[12]  Philipp Koehn,et al.  Explorer Edinburgh System Description for the 2005 IWSLT Speech Translation Evaluation , 2005 .

[13]  Arianna Bisazza,et al.  Fill-up versus interpolation methods for phrase-based SMT adaptation , 2011, IWSLT.

[14]  Mauro Cettolo.  Segmentation, classification and clustering of an Italian broadcast news corpus , 2000 .

[15]  Mark J. F. Gales,et al.  Maximum likelihood linear transformations for HMM-based speech recognition , 1998, Comput. Speech Lang..

[16]  Fabio Brugnara,et al.  Improved automatic speech recognition through speaker normalization , 2006, Comput. Speech Lang..

[17]  Sebastian Stüker,et al.  Overview of the IWSLT 2011 evaluation campaign , 2011, IWSLT.

[18]  Joel D. Martin,et al.  Improving Translation Quality by Discarding Most of the Phrasetable , 2007, EMNLP.

[19]  Philipp Koehn,et al.  Moses: Open Source Toolkit for Statistical Machine Translation , 2007, ACL.

[20]  Christoph Tillmann,et al.  A Unigram Orientation Model for Statistical Machine Translation , 2004, NAACL.

[21]  Franz Josef Och,et al.  Minimum Error Rate Training in Statistical Machine Translation , 2003, ACL.