@inproceedings{1be7286167144c06ad5bdb017a16c7ec,
title = "Speech recognition of under-resourced languages using mismatched transcriptions",
abstract = "Mismatched crowdsourcing is a technique to derive speech transcriptions using crowd-workers unfamiliar with the language being spoken. This technique is especially useful for under-resourced languages since it is hard to hire native transcribers. In this paper, we demonstrate that using mismatched transcription for adaptation improves performance of speech recognition under limited matched training data conditions. In addition, we show that using data augmentation improves not only performance of monolingual system but also makes mismatched transcription adaptation more effective.",
keywords = "data augmentation, mismatched transcription, model adaptation, speech recognition, under-resourced language",
author = "Do, {Van Hai} and Chen, {Nancy F.} and Lim, {Boon Pang} and Mark Hasegawa-Johnson",
note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 20th International Conference on Asian Language Processing, IALP 2016 ; Conference date: 21-11-2016 Through 23-11-2016",
year = "2017",
month = mar,
day = "10",
doi = "10.1109/IALP.2016.7875947",
language = "English (US)",
series = "Proceedings of the 2016 International Conference on Asian Language Processing, IALP 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "112--115",
editor = "Minghui Dong and Chung-Hsien Wu and Yanfeng Lu and Haizhou Li and Yuen-Hsien Tseng and Liang-Chih Yu and Lung-Hao Lee",
booktitle = "Proceedings of the 2016 International Conference on Asian Language Processing, IALP 2016",
address = "United States",
}