Phoneme discrimination using KS algebra I
This work addresses phoneme discrimination for speech processing applications, but appears incremental as it substitutes fuzzy logic with a new algebra without clear evidence of broad impact.
The authors tackled the problem of phoneme discrimination by defining a new algebra of operators as a substitute for fuzzy logic, resulting in a method optimized for constructing binary discriminators based on spectral content using operations like min, max, difference, and generalized additively homogeneous means.
In our work we define a new algebra of operators as a substitute for fuzzy logic. Its primary purpose is for construction of binary discriminators for phonemes based on spectral content. It is optimized for design of non-parametric computational circuits, and makes uses of 4 operations: $\min$, $\max$, the difference and generalized additively homogenuous means.