@inproceedings{junczys-dowmunt2015large,
author = {Junczys-Dowmunt, Marcin and Przybysz, Paweł and Staszuk, Arleta and Kim, Eun-Kyoung and Lee, Jaewon},
title = {Large Scale Speech-to-Text Translation with Out-of-Domain Corpora Using Better Context-Based Models and Domain Adaptation},
booktitle = {INTERSPEECH 2015 - 16th Annual Conference of the International Speech Communication Association},
year = {2015},
month = {September},
abstract = {In this paper, we described the process of building a large-scale speech-to-text pipeline. Two target domains, daily conversations and travel-related conversations between two agents, for the English-German language pair (both directions) are examined. The SMT component is built from out-of-domain but freely-available bilingual and monolingual data. We make use of most of the known available resources to examine the effects of unrestricted data and large scale models. A naive baseline delivers solid results in terms of MT-quality. Extending the baseline with context-based translation model features like operations sequence models, higher-order class-based language models, and additional web-scale word-based language models leads to a system that significantly outperforms the baseline. Domain adaption is performed by separately weighting the influence of the out-of-domain subcorpora. This is explored for translation models and language models yielding significant improvements in both cases. Automatic and manual evaluation results are provided for raw MT-quality and ASR+MT-quality.},
url = {http://approjects.co.za/?big=en-us/research/publication/large-scale-speech-text-translation-domain-corpora-using-better-context-based-models-domain-adaptation/},
edition = {INTERSPEECH 2015 - 16th Annual Conference of the International Speech Communication Association},
}