Combining Adversarial Training and Disentangled Speech Representation for Robust Zero-Resource Subword Modeling
Combining Adversarial Training and Disentangled Speech Representation for Robust Zero-Resource Subword Modeling
This study addresses the problem of unsupervised subword unit discovery from untranscribed speech.It forms the basis of the ultimate goal of ZeroSpeech 2019, building text-to-speech systems without text labels.In this work, unit discovery is formulated as a pipeline of phonetically discriminative feature learning and unit inference.One major difficulty in robust …