Zero-Cost Speech Recognition Task at Mediaeval 2016

The main goal of the Zero-Cost Speech Recognition task isto bring researchers together on the topic of training ASRsystems using only publicly available data. In particular,the task consists on the development of either an LVCSRor a subword speech recognizer on a given target language.For this year we selected Vietnamese as the target languageThe organizers provided participants several sets of pub-licly available data combined with one proprietary set gath-ered for this evaluation. Participants are free to find anduse other publicly available resources (free for research pur-poses). These resources must be shared with other partici-pants till end of July. The data-set for the evaluation is thenfixed and no outside data can be used.