Publication Details
Improving Language Models for ASR Using Translated In-domain Data
Mikolov Tomáš, Ing. (DCGM FIT BUT)
Karafiát Martin, Ing., Ph.D. (DCGM FIT BUT)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Low Resource ASR, Language Modeling, Machine Translation
This paper descibes how to do the acquisition of in-domain training data for the puspose of building speech recognition systems for under-resourced languages.
Acquisition of in-domain training data to build speech recognition systems for under-resourced languages can be a costly, time-demanding and tedious process. In this work, we propose the use of machine translation to translate English transcripts of telephone speech into Czech language in order to improve a Czech CTS speech recognition system. The translated transcripts are used as additional language model training data in a scenario where the baseline language model is trained on off- and close-domain data only. We report perplexities, OOV and word error rates and examine different data sets and translators on their suitability for the described task.
@INPROCEEDINGS{FITPUB9927,
author = "Stefan Kombrink and Tom\'{a}\v{s} Mikolov and Martin Karafi\'{a}t and Luk\'{a}\v{s} Burget",
title = "Improving Language Models for ASR Using Translated In-domain Data",
pages = "4405--4408",
booktitle = "Proceedings of 2012 IEEE International Conference on Acoustics, Speech and Signal Processing",
year = 2012,
location = "Kyoto, JP",
publisher = "IEEE Signal Processing Society",
ISBN = "978-1-4673-0044-5",
doi = "10.1109/ICASSP.2012.6288896",
language = "english",
url = "https://www.fit.vut.cz/research/publication/9927"
}