ISCA Archive Interspeech 2013
ISCA Archive Interspeech 2013

Graph-based semi-supervised learning for phone and segment classification

Yuzong Liu, Katrin Kirchhoff

This paper presents several novel contributions to the emerging framework of graph-based semi-supervised learning for speech processing. First, we apply graph-based learning to variable-length segments rather than to the fixed-length vector representations that have been used previously. As part of this work we compare various graph-based learners, and we utilize an efficient feature selection technique for high-dimensional feature spaces that alleviates computational costs and improves the performance of graph-based learners. Finally, we present a method to improve regularization during the learning process. Experimental evaluation on the TIMIT frame and segment classification tasks demonstrates that the graph-based classifiers outperform standard baseline classifiers; furthermore, we find that the best learning algorithms are those that can incorporate prior knowledge.

doi: 10.21437/Interspeech.2013-453

Cite as: Liu, Y., Kirchhoff, K. (2013) Graph-based semi-supervised learning for phone and segment classification. Proc. Interspeech 2013, 1840-1843, doi: 10.21437/Interspeech.2013-453

  author={Yuzong Liu and Katrin Kirchhoff},
  title={{Graph-based semi-supervised learning for phone and segment classification}},
  booktitle={Proc. Interspeech 2013},