Real time feature extraction of acoustic signals with an analog neural computer

The majority of neural network based speech recognition models currently employed are simulated on digital computers. While appropriate for the laboratory environment, low cost digital computers do not have the computational power required to simulate neural network recognition systems in real time. Speech recognition models based on neural networks can be realized in analog hardware where circuits can be made that operate in real-time. This paper presents results from an on-going project to implement a speech recognition system on a general purpose analog neurocomputer. In particular, the input stages of the recognition system are presented. These stages consist of analog band-pass filters and feature detectors for energy onset, offset, motion, pause, and duration