Phoneme discrimination using KS algebra I

TL;DR

This paper introduces a new algebraic framework using four operations to build binary phoneme discriminators based on spectral content, aiming to improve non-parametric computational circuits.

Contribution

It proposes a novel algebraic system as an alternative to fuzzy logic for phoneme discrimination, focusing on spectral analysis and circuit design.

Findings

Defines a new algebra of operators for phoneme discrimination

Optimized for non-parametric computational circuit design

Uses four specific operations: min, max, difference, and generalized means

Abstract

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.