The Zero Resource Speech Challenge 2017
This work addresses the challenge of unsupervised speech processing for researchers in speech technology, but it is incremental as a follow-up to a 2015 version.
The paper introduced the Zero Resource Speech Challenge 2017, which tackled the problem of discovering subword and word units from raw speech without text or labels, and presented results from seventeen models evaluated on cross-language and speaker adaptation tasks.
We describe a new challenge aimed at discovering subword and word units from raw speech. This challenge is the followup to the Zero Resource Speech Challenge 2015. It aims at constructing systems that generalize across languages and adapt to new speakers. The design features and evaluation metrics of the challenge are presented and the results of seventeen models are discussed.