Modeling under-resourced languages for speech recognition

Loading...
Thumbnail Image
Journal Title
Journal ISSN
Volume Title
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
Date
2017-12
Major/Subject
Mcode
Degree programme
Language
en
Pages
27
1-27
Series
LANGUAGE RESOURCES AND EVALUATION
Abstract
One particular problem in large vocabulary continuous speech recognition for low-resourced languages is finding relevant training data for the statistical language models. Large amount of data is required, because models should estimate the probability for all possible word sequences. For Finnish, Estonian and the other fenno-ugric languages a special problem with the data is the huge amount of different word forms that are common in normal speech. The same problem exists also in other language technology applications such as machine translation, information retrieval, and in some extent also in other morphologically rich languages. In this paper we present methods and evaluations in four recent language modeling topics: selecting conversational data from the Internet, adapting models for foreign words, multi-domain and adapted neural network language modeling, and decoding with subword units. Our evaluations show that the same methods work in more than one language and that they scale down to smaller data resources.
Description
Keywords
Adaptation, Data filtering, Large vocabulary speech recognition, Statistical language modeling, Subword units
Other note
Citation
Kurimo , M , Enarvi , S , Tilk , O , Varjokallio , M , Mansikkaniemi , A & Alumäe , T 2017 , ' Modeling under-resourced languages for speech recognition ' , LANGUAGE RESOURCES AND EVALUATION , vol. 51 , no. 4 , pp. 961-987 . https://doi.org/10.1007/s10579-016-9336-9