Acoustic modeling with neural graph embeddings
ASRU, pp. 581-588, 2015.
Graph-based learning (GBL) is a form of semi-supervised learning that has been successfully exploited in acoustic modeling in the past. It utilizes manifold information in speech data that is represented as a joint similarity graph over training and test samples. Typically, GBL is used at the output level of an acoustic classifier; howeve...More
Full Text (Upload PDF)
PPT (Upload PPT)