HQSYN16

So far, the unit selection is driven by hand-tuned set of features and costs of their mismatch. To automatize the prediction of join smoothness, with the advantage of automatic per-speaker tuning, we have tried to employ one class classification approach, with the classifiers trained on the natural (and thus smooth) unit transitions from the source speech corpus. We have focused on vowels due to their signal stability at the point of concatenation. Unfortunately, this approach did not lead to the expected results.