The ZeroSpeech challenge targets the unsupervised discovery of linguistic units from raw speech in an unknown language. As in the 2015 edition, it concerns two core components: the discovery of subword units (Track 1) and the discovery of word units (Track 2), respectively. For both tracks, the same evaluation metrics as in the former edition are used.
More information can be found at www.zerospeech.comRead more
Contributions are accepted from participants of the challenge.