Speech corpora do not exist for most low-resource languages. Thus, creating speech corpora for a language of such a nature is challenging and involves a significant amount of time and effort.
A neural network based intent classification system for a specific domain that has the capability to identify the intent of an uttered command in Sinhala language without converting to text. Two research papers were submitted. A mobile web app was developed for collecting voice samples.
Building an open domain automatic speech recognition(ASR) system can be accomplished by converting voice into text and performing a text classification on top of the converted text.