@inproceedings{L16-1124,
 abstract = {In this paper the authors present a speech corpus designed and created for the development and evaluation of dictation systems in Latvian. The corpus consists of over nine hours of orthographically annotated speech from 30 different speakers. The corpus features spoken commands that are common for dictation systems for text editors. The corpus is evaluated in an automatic speech recognition scenario. Evaluation results in an ASR dictation scenario show that the addition of the corpus to the acoustic model training data in combination with language model adaptation allows to decrease the WER by up to relative 41.36\% (or 16.83\% in absolute numbers) compared to a baseline system without language model adaptation. Contribution of acoustic data augmentation is at relative 12.57\% (or 3.43\% absolute).
},
 address = {Portorož, Slovenia},
 author = {Mārcis Pinnis and Askars Salimbajevs and Ilze Auzina},
 booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
 month = {May},
 pages = {775--780},
 publisher = {European Language Resources Association (ELRA)},
 title = {Designing a Speech Corpus for the Development and Evaluation of Dictation Systems in Latvian},
 url = {https://www.aclweb.org/anthology/L16-1124},
 year = {2016}
}