Speech processing in the human brain is a very complex process far from being fully understood although much progress
has been done recently. Neuromorphic Speech Processing is a new research orientation in bio-inspired systems approach
to find solutions to automatic treatment of specific problems (recognition, synthesis, segmentation, diarization, etc)
which can not be adequately solved using classical algorithms. In this paper a neuromorphic speech processing
architecture is presented. The systematic bottom-up synthesis of layered structures reproduce the dynamic feature
detection of speech related to plausible neural circuits which work as interpretation centres located in the Auditory
Cortex. The elementary model is based on Hebbian neuron-like units. For the computation of the architecture a flexible
framework is proposed in the environment of Matlab®/Simulink®/HDL, which allows building models in different
description styles, complexity and implementation levels. It provides a flexible platform for experimenting on the
influence of the number of neurons and interconnections, in the precision of the results and in performance evaluation.
The experimentation with different architecture configurations may help both in better understanding how neural circuits
may work in the brain as well as in how speech processing can benefit from this understanding.