First European Conference on Speech Communication and Technology

Paris, France
September 27-29, 1989

Comparison of Symbolic and Connectionist Approaches to Eliminate Coarticulation Effects in Phonemic Speech Recognition

Kari Torkkola, Kimmo Raivio

Helsinki University of Technology, Laboratory of Information and Computer Science, Espoo, Finland

Two methods to correct phonemic transcriptions produced by the acoustic processor of a speech recognition system are described and compared. The first method that was invented by Prof. Teuvo Kohonen and named the Dynamically Expanding Context (DEC), involves a large set of error-correcting rules automatically constructed from examples. This symbolic approach is compared with a connectionist one, which employs a multi-layered feed-forward network trained with back propagation. Our experiments demonstrate that the latter paradigm is far from optimal when context-dependent mapping (e.g. correction) from one set of symbol strings to another is desired. The DEC-method is shown to have better correction capabilities. Beside this, the training time required by DEC is a fraction of that required by back propagation.

Full Paper

Bibliographic reference.  Torkkola, Kari / Raivio, Kimmo (1989): "Comparison of symbolic and connectionist approaches to eliminate coarticulation effects in phonemic speech recognition", In EUROSPEECH-1989, 1009-1012.