A Neural Network Based Speech Recognition System
Abstract
This report presents an overview of the development of a neural network based speech recognition system. The two primary tasks involved were the development of a time invariant speech encoder and a pattern recognizer or detector. The speech encoder uses amplitude normalization and a Fast Fourier Transform to eliminate amplitude and frequency shifts of acoustic clues. The detector consists of a back-propagation network which accepts data from the encoder and identifies individual words. This use of neural networks offers two advantages over conventional algorithmic detectors: the detection time is no more than a few network time constants, and its recognition speed is independent of the number of the words in the vocabulary. The completed system has functioned as expected with high tolerance to input variation and with error rates comparable to a commercial system when used in a noisy environment. Keywords: Artificial intelligence; Neural networks: Back propagation; Speech recognition.
Document Details
- Document Type
- Technical Report
- Publication Date
- Feb 01, 1990
- Accession Number
- ADA219794
Entities
People
- Edward J. Carrol
- G. N. Reddy
- Norman P. Coleman Jr.
Organizations
- United States Army Armament Research, Development and Engineering Center