Large vocabulary ASR for spontaneous Czech in the MALACH project (2003)
| Venue: | In Proceedings of the 8th European Conference on Speech Communication and |
| Citations: | 3 - 0 self |
BibTeX
@INPROCEEDINGS{Psutka03largevocabulary,
author = {Josef Psutka and Pavel Ircing and J. V. Psutka and Vlasta Radová and William J. Byrne and Jan Hajic and Jirí Mírovsky and Samuel Gustman},
title = {Large vocabulary ASR for spontaneous Czech in the MALACH project},
booktitle = {In Proceedings of the 8th European Conference on Speech Communication and},
year = {2003}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
This paper describes LVCSR research into the automatic transcription of spontaneous Czech speech in the MALACH (Multilingual Access to Large Spoken Archives) project. This project attempts to provide improved access to the large multilingual spoken archives collected by the Survivors of the Shoah Visual History Foundation (VHF) (www.vhf.org) by advancing the state of the art in automated speech recognition. We describe a baseline ASR system and discuss the problems in language modeling that arise from the nature of Czech as a highly inflectional language that also exhibits diglossia between its written and spontaneous forms. The difficulties of this task are compounded by heavily accented, emotional and disfluent speech along with frequent switching between languages. To overcome the limited amount of relevant language model data we use statistical techniques for selecting an appropriate training corpus from a large unstructured text collection resulting in significant reductions in word error rate. 1.
Citations
| 449 | SRILM – an extensible language modeling toolkit - Stolcke - 2002 |
| 17 | Using out-of-domain data to improve in-domain language models - Iyer, Ostendorf, et al. - 1997 |
| 3 | Two-Pass Recognition of Czech Speech Using Adaptive Vocabulary - Icring, Psutka - 2001 |
| 1 | Automatic Transcription of Speaking Styles - Ramabhadran, Picheny, et al. |
