Acoustic modeling with neural graph embeddings

ASRU, pp. 581-588, 2015.

Cited by: 6|Bibtex|Views5
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com

Abstract:

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

Code:

Data:

Your rating :
0

 

Tags
Comments