@inproceedings{03c0d39b3126474f9cbcc6cfcc73786d,
title = "Information retrieval test collection for searching spontaneous Czech speech",
abstract = "This paper describes the design of the first large-scale IR test collection built for the Czech language. The creation of this collection also happens to be very challenging, as it is based on a continuous text stream from automatic transcription of spontaneous speech and thus lacks clearly defined document boundaries. All aspects of the collection building are presented, together with some general findings of initial experiments.",
author = "Pavel Ircing and Pavel Pecina and Oard, \{Douglas W.\} and Jianqiang Wang and White, \{Ryen W.\} and Jan Hoidekr",
year = "2007",
doi = "10.1007/978-3-540-74628-7\_57",
language = "English",
isbn = "9783540746270",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "439--446",
booktitle = "Text, Speech and Dialogue - 10th International Conference, TSD 2007, Proceedings",
address = "Germany",
note = "10th International Conference on Text, Speech and Dialogue, TSD 2007 ; Conference date: 03-09-2007 Through 07-09-2007",
}