YAST: A Scalable ASR Toolkit Especially Designed for Under-Resourced Languages

The ability to collect and process a large amount of resources (e.g. vocabularies, text corpora, transcribed speech corpora and phonetic dictionaries) constitutes a critical prerequisite of systems based on statistical methods. This aspect becomes crucial for languages presenting a lack of computer resources, also known as under-resourced languages, such as Vietnamese. Our work consists in exploring an efficient methodology which can help the development of speech recognition systems for this kind of languages. This article presents a possible solution that provides a fast building and customisable ASR toolkit, called YAST. The latter includes an ASR library as well as a collection of C++/Java executable programs and some helper bash and perl scripts. These utilities allow on one hand, to build and evaluate an ASR system, on the other, to provide programming development hooks that permit to include state of the art techniques. YAST is freely available for non-commercial purposes. This paper summarizes the functionality of the toolkit and also provides a basic example carried out on the Vietnamese language.