Publication Details
Grapheme Based Speech Recognition
speech recognition, LVCSR, ASR, grapheme, phoneme, low-resource languages
This article describes the results of grapheme-based speech recognition for eight languages. We used this approach due to the situation of low resource languages.
This article presents the results of grapheme-based speech recognition for eight languages. The need for this approach arises in situation of low resource languages, where obtaining a pronunciation dictionary is time- and cost-consuming or impossible. In such scenarios, usage of grapheme dictionaries is the most simplest and straight-forward. The paper describes the process of automatic generation of pronunciation dictionaries with emphasis on the expansion of numbers. Experiments on GlobalPhone database show that grapheme-based systems have results comparable to the phonemebased ones, especially for phonetic languages.
@inproceedings{BUT96985,
author="Miloš {Janda}",
title="Grapheme Based Speech Recognition",
booktitle="Proceedings of the 18th Conference STUDENT EEICT 2012",
year="2012",
pages="441--445",
publisher="Brno University of Technology",
address="Brno",
isbn="978-80-214-4460-7",
url="http://www.feec.vutbr.cz/EEICT/2012/sbornik/03doktorskeprojekty/09grafikaamultimedia/02-xjanda16.pdf"
}