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.

Date Published: 3 May 2011
PDF: 10 pages
Proc. SPIE 8068, Bioelectronics, Biomedical, and Bioinspired Systems V; and Nanotechnology V, 80680H (3 May 2011); doi: 10.1117/12.885460

Published in SPIE Proceedings Vol. 8068:
Bioelectronics, Biomedical, and Bioinspired Systems V; and Nanotechnology V
Ángel B. Rodríguez-Vázquez; Rainer Adelung, Editor(s)