8th Annual Conference of the International Speech Communication Association

Antwerp, Belgium
August 27-31, 2007

Semi-Supervised Learning of Speech Sounds

Aren Jansen, Partha Niyogi

University of Chicago, USA

Recently, there has been much interest in both semi-supervised and manifold learning algorithms, though their applicability has not been explored for all domains. This paper has two goals: (i) to demonstrate semi-supervised approaches based solely on clustering are insufficient for phoneme classification and (ii) to present a new manifold-based semi-supervised algorithm to remedy this shortcoming. The improved performance of our approach over cluster-based methods substantiates the practical relevance of a geometric perspective on speech sounds.

Full Paper

Bibliographic reference.  Jansen, Aren / Niyogi, Partha (2007): "Semi-supervised learning of speech sounds", In INTERSPEECH-2007, 86-89.