7th International Conference on Spoken Language Processing

September 16-20, 2002
Denver, Colorado, USA

Framewise Phone Classification Using Support Vector Machines

Jesper Salomon (1), Simon King (2), Jesper Salomon (2)

(1) Technical University of Denmark, Denmark; (2) University of Edinburgh, U.K.

We describe the use of Support Vector Machines for phonetic classi- fication on the TIMIT corpus. Unlike previous work, in which entire phonemes are classified, our system operates in a framewise manner and is intended for use as the front-end of a hybrid system similar to ABBOT. We therefore avoid the problems of classifying variablelength vectors. Our frame-level phone classification accuracy on the complete TIMIT test set is competitive with other results from the literature. In addition, we address the serious problem of scaling Support Vector Machines by using the Kernel Fisher Discriminant.

Full Paper

Bibliographic reference.  Salomon, Jesper / King, Simon / Salomon, Jesper (2002): "Framewise phone classification using support vector machines", In ICSLP-2002, 2645-2648.