@inproceedings{a395fe4f224b460380ec8c74f23891d4,
title = "Designing the latvian speech recognition corpus",
abstract = "In this paper the authors present the first Latvian speech corpus designed specifically for speech recognition purposes. The paper outlines the decisions made in the corpus designing process through analysis of related work on speech corpora creation for different languages. The authors provide also guidelines that were used for the creation of the Latvian speech recognition corpus. The corpus creation guidelines are fairly general for them to be re-used by other researchers when working on different language speech recognition corpora. The corpus consists of two parts - an orthographically annotated corpus containing 100 hours of orthographically transcribed audio data and a phonetically annotated corpus containing 4 hours of phonetically transcribed audio data. Metadata files in XML format provide additional details about the speakers, noise levels, speech styles, etc. The speech recognition corpus is phonetically balanced and phonetically rich and the paper describes also the methodology how the phonetical balancedness has been assessed.",
keywords = "Corpus creation guidelines, Latvian, Speech recognition corpus",
author = "Marcis Pinnis and Ilze Auziņa and Karlis Goba",
year = "2014",
language = "English",
series = "Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014",
publisher = "European Language Resources Association (ELRA)",
pages = "1547--1553",
editor = "Nicoletta Calzolari and Khalid Choukri and Sara Goggi and Thierry Declerck and Joseph Mariani and Bente Maegaard and Asuncion Moreno and Jan Odijk and Helene Mazo and Stelios Piperidis and Hrafn Loftsson",
booktitle = "Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014",
note = "9th International Conference on Language Resources and Evaluation, LREC 2014 ; Conference date: 26-05-2014 Through 31-05-2014",
}